Personalized alert generation based on information distribution

Abstract

The system includes a memory and a processor in communication with the memory. The processor may be configured to perform operations including: analyzing interactions by a user in a network; and generating a user profile for the user. The operations by the processor may further include identifying attempts by the user to share a post over the network; and prompting the user to rate the post with a personalized alert, where the personalized alert is generated based on the interactions, the user profile, and properties of the post.

Description

[Technical Field]

[0001] FIELD OF THE DISCLOSURE The present disclosure relates to information distribution, and more particularly to generating personalized alerts prior to information distribution. [Background technology]

[0002] Technology allows for the rapid and easy dissemination of information, which may or may not be factually accurate. Additionally, machine learning is prevalent in technology, and machine learning can automatically update and improve functionality by analyzing information and relevance. Summary of the Invention [Means for solving the problem]

[0003] Embodiments of the present disclosure include systems, methods, and computer program products for personalized alerts. The embodiments may include a processor configured to perform operations. The operations may include analyzing interactions by a user in a network and generating a user profile for the user. The operations may further include identifying attempts by the user to share a post via the network and prompting the user to rate the post with a personalized alert, where the personalized alert is generated based on the interactions, the user profile, and properties of the post.

[0004] In some embodiments, defining the user profile includes evaluating how the user interacts with the network, where evaluating how the user interacts with the network takes into account the user's scrolling speed, the amount of interaction the user has with content on the network, and the time between the user's interactions with the content on the network.

[0005] In some embodiments, the interactions and the user profile are user data included in a corpus, the properties of the posts are included in the corpus, the corpus is used to train a machine learning algorithm, and the machine learning algorithm generates the personalized alert. Some embodiments may further include receiving feedback from the user; and integrating the feedback into the corpus.

[0006] Some embodiments further include analyzing the interaction with the content on the network; and assessing a response of the user based on the interaction.

[0007] In some embodiments, the properties of the post include the topic of the post and the popularity of the post.

[0008] Some embodiments may further include analyzing the property, identifying one or more characteristics based on the property, comparing the property to one or more historical properties, and determining that the property is at or above a reputation threshold. In some embodiments, the properties of the post may include the reputability of the origin of the post and the factual contentiousness of the post.

[0009] The above summary is not intended to describe each illustrated embodiment or every implementation of the present disclosure.

[0010] The drawings contained herein are incorporated into and constitute a part of this specification. They illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure. The drawings are merely illustrative of certain embodiments and are not intended to limit the disclosure. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 illustrates a representative system of components according to some embodiments of the present disclosure. [Figure 2] FIG. 2 illustrates a flow chart diagram for generating an analytical engagement according to some embodiments of the present disclosure. [Figure 3] FIG. 3 illustrates a system decision tree according to some embodiments of the present disclosure. [Figure 4] FIG. 4 illustrates a flowchart diagram of data compilation according to some embodiments of the present disclosure. [Figure 5] FIG. 5 illustrates a cloud computing environment according to an embodiment of the present invention. [Figure 6] FIG. 6 illustrates abstraction model layers according to one embodiment of the present invention. [Figure 7] FIG. 7 illustrates a high-level block diagram of an exemplary computer system that may be used to implement one or more of the methods, tools, and modules, and any associated functionality, described herein, according to embodiments of the present disclosure.

[0012] While the invention is amenable to various modifications and alternative forms, specific features thereof have been shown by way of example in the drawings and will be described in detail. It should be understood, however, that there is no intention to limit the invention to the particular embodiments described. On the contrary, it is intended to cover all modifications, equivalents, and alternatives falling within the scope of the invention. DETAILED DESCRIPTION OF THE INVENTION

[0013] Aspects of the present disclosure relate to information distribution, and more particularly, to generating personalized alerts prior to information distribution.

[0014] Individuals can access information, or distribute information, or access and distribute information. Information can be accessed or disseminated, or accessed and disseminated, regardless of whether the information is factually accurate. Analytical thinking allows individuals to avoid thoughtless acceptance of consumed information and to evaluate the veracity of information before disseminating it. Thus, analytical thinking can slow the spread of inaccurate material by encouraging individuals to proactively decide whether to distribute information. Therefore, encouraging analytical thinking at the time of information consumption, or information distribution, or consumption and distribution, can slow the spread of inaccurate information.

[0015] Embodiments of the present disclosure may encourage individuals to engage in analytical thinking at the time of information consumption or distribution, or consumption and distribution, thereby reducing the distribution of factually inaccurate information. Thus, embodiments of the present disclosure may promote the intellectual growth of individuals and slow the spread of factually inaccurate information, while reducing or eliminating the impact of unkind speech.

[0016]

[0003] Embodiments of the present disclosure include a system, method, and computer program product for personalized alerts to engage analytical thinking before disseminating information. The system includes a memory and a processor in communication with the memory. The processor may be configured to perform operations including analyzing interactions by a user in a network and generating a user profile for the user. The operations by the processor may further include identifying attempts by the user to share a post over the network and prompting the user to rate the post with a personalized alert, where the personalized alert is generated based on the interactions, the user profile, and properties of the post.

[0017] 1 illustrates a system 100 of representative components according to some embodiments of the present disclosure. A user 110 may submit input to a user device 120. The user device 120 may submit the user's 110 input to a network system 130. The network system 130 may make the user's 110 input available to a proactive agent 150. The proactive agent 150 may encourage the user 110 to engage in analytical thinking.

[0018] A user 110 may submit input to a user device 120 capable of communicating with a network system 130. Embodiments of the present disclosure may be used with devices and systems currently in use or that may be later developed. A user device 120 may be, for example, a mobile phone, a computer, a communication device (e.g., a headset or a data entry portal), a bot (e.g., a smart hub device) configured to communicate with a network system, etc.

[0019] The user device 120 may communicate with a network system 130. The network system 130 connects the devices to one another. The network system 130 may be a system through which the user 110 may interact, directly or indirectly, with one or more other individuals. The network system 130 may be, for example, a communications network, a website (e.g., an internet chat room), a communications client (e.g., a mobile application for communicating with other individuals), or a social network system (e.g., a social media platform).

[0020] The network system 130 may communicate with a proactive agent 150. The proactive agent 150 may encourage the user 110 to engage in analytical thinking. The proactive agent 150 may encourage analytical thinking, for example, by posting relevant questions for the user 110 to consider. The proactive agent 150 may collect information to evaluate which questions to pose to encourage the user 110 to engage in analytical thinking. The information may include, for example, how the user 110 has answered similar questions, the user's 110's estimated biases about particular posts, feedback from the user 110, etc.

[0021] For example, proactive agent 150 may include data in data corpus 151 that correlates the presentation of "why" questions to user 110 with the delay between when user 110 accesses information and when user 110 shares the information, while "how" questions are not correlated with the delay between when user 110 accesses information and when user 110 shares the information. As a result, proactive agent 150 may conclude that user 110 is more likely to engage in analytical thinking when "why" questions are posted than when "how" questions are posted. Such a conclusion may result in proactive agent 150 increasing the frequency of "why" questions and decreasing the frequency of "how" questions.

[0022] The proactive agent 150 may include a data corpus 151, a profile analyzer 152, a context extractor 154, a question generator 156, or a feedback module 158, or any combination thereof. The proactive agent 150 may include a data corpus 151 for storing collected data for question development, question data, user preferences, user data, user feedback, question recommendations, machine learning (ML) models, etc. The data corpus 151 may be used to develop questions or ML models for developing questions to provide personalized alerts to engage the user 110 in analytical thinking, or any combination thereof. The data corpus 151 may draw information from various sources, such as direct input from the user 110, one or more profiles that the user 110 selects for analysis, a storage device, the Internet, etc.

[0023] Proactive agent 150 may include a profile analyzer 152 for analyzing user data. Profile analyzer 152 may retrieve information contained in data corpus 151 for analysis. For example, a profile may be retrieved and stored in data corpus 151, and profile analyzer 152 may analyze the profile while it is in data corpus 151. Profile analyzer 152 may provide data to data corpus 151. For example, profile analyzer 152 retrieves profile data from data corpus 151 or another source, analyzes the profile data, and submits the profile data, insights gained from analyzing the profile data, or a combination thereof, to data corpus 151.

[0024] In some embodiments, proactive agent 150 may include a context extractor 154. Context extractor 154 may extract the context of a post viewed by user 110. Context extractor 154 may use the context of the post to assist in determining whether user 110 may experience partiality with the post. In cooperation with profile analyzer 152, context extractor 154 may also assist in determining what partiality the user may experience with the post. Identifying one or more potential partialities may assist question generator 156 in generating personalized questions for user 110 to engage user 110 in analytical thinking regarding the post that user 110 is currently viewing.

[0025] Insights obtained from the profile analyzer 152 analyzing the profile data and the context extractor 154 extracting the posted content may be stored in the data corpus 151 for use by the question generator 156. The question generator 156 may generate personalized questions to engage the user 110 in analytical thinking. The profile data, the posted content, the insights generated by the profile analyzer 152, or the insights obtained by the context extractor 154, or a combination thereof, may be used to generate questions directly or to generate data that can then be used to generate questions. The questions generated by the question generator 156 may be used to engage the user 110 in analytical thinking about the posts. In some embodiments, the proactive agent 150 may prompt the user 110 with questions when the user 110 is considering sharing content.

[0026] The question generator 156 may prompt the user 110 with one or more questions depending on the collected data, insights generated from the context of the post determined by the context extractor 154, insights generated from the profile data determined by the profile analyzer 152, or some combination thereof. The questions may prompt the user 110 to ask, for example, how the post made the user 110 feel, whether the user 110 has seen similar content hosted by other sources, and whether the user 110 considers the source to be trustworthy.

[0027] The question generator 156 may select one or more questions to present to the user 110 from a set of pre-loaded questions. For example, the data corpus 151 may include questions curated by experts to maximize their ability to evoke analytical responses from the user 110. The questions included in the data corpus 151 may be entirely curated by experts, mostly curated by experts, partially curated by experts, or derived from expert-curated questions. In some embodiments, the question generator 156 may select one or more questions from a list of expert-curated questions in the data corpus 151 to display to the user 110 and engage the user 110 in analytical thinking. In some embodiments, the question generator 156 may incorporate data about the user 110, the content of the post, or a combination thereof, to select one or more questions from the list of expert-curated questions.

[0028] Proactive agent 150 may further include a feedback module 158. Feedback module 158 may provide a mechanism for user 110 to provide feedback to proactive agent 150, either directly or indirectly. Feedback submitted by user 110 may be integrated into data corpus 151, used to adjust proactive agent 150, or integrated into data corpus 151 and used to adjust proactive agent 150. For example, user 110 may provide feedback through feedback module 158 that proactive agent 150 is asking too many questions and should ask fewer questions to improve its effectiveness; proactive agent 150 may integrate this information into data corpus 151 and reduce the number of questions in a standard prompt from four to three.

[0029] In some embodiments, the interactions and user profile of user 110 are user data included in data corpus 151. In some embodiments, properties of the posts (e.g., contextual insights generated by context extractor 154) are included in data corpus 151. In some embodiments, data corpus 151 may be used to train an algorithm (e.g., an ML algorithm), where the ML algorithm may include question generator 156 that generates personalized alerts for user 110. Some embodiments may further include receiving feedback from the user and integrating the feedback into the corpus.

[0030] 2 illustrates a flowchart diagram of a process 200 for generating analytical engagements according to some embodiments of the present disclosure. Process 200 may include identifying data (step 202), determining session metrics (step 230), inputting the data into a model (step 240), and outputting prompts (step 250). Process 200 may be performed, in whole or in part, by a processor.

[0031] Identifying the data (step 202) may include analyzing the user data (step 210). The user data may comprise user profile data 212, or user interaction data 214, or a combination thereof. The user profile data 212 may include information about the user collected from a user profile. The user profile data 212 may include, for example, the user's demographics, affiliations, geography, interests, work history, favorite books, etc. The user interaction data 214 may include actions by the user to interact with the platform or service. The user interaction data 214 may include, for example, the user's likes, comments, and shares; the user's scrolling speed; the user's clicks over time; the user's reactions over time; and similar information.

[0032] Analyzing the user data (step 210) may result in evaluating a user profile based on the user information. The user profile may be evaluated using user history information, current user information, or a combination thereof. In some embodiments, user history information may be used to evaluate the user profile, and information from the user's current session may be compared to the user profile to evaluate the user's deviation from historical use. In some embodiments, the system may associate deviations from the historically derived profile as deviations in the user's disposition and may modify the output accordingly. For example, data indicating a deviation by the user may indicate that the user is frustrated, and therefore the system would output one question instead of three questions to encourage analytical thinking.

[0033] In some embodiments, a user profile may be defined, and defining a user profile may include evaluating how the user interacts with the network. Evaluating how the user interacts with the network may take into account the user's scrolling speed, the amount of interaction the user has with content on the network, and the time between the user's interactions with the content on the network.

[0034] In some embodiments, the user profile may include various details about the user. Details about the user may be referred to as user data. User data may include one or more of the user's activities, such as likes, shares, or comments, or a combination thereof. User data may include one or more of the user's connections, such as affiliations, interests, and influences. The data collected or used in personalization, or the data collected and used, may be set according to default settings, set by the user, or some combination thereof. For example, a user may decide that information about the user's likes may be collected and used, but information about the user's shares will not be collected or used.

[0035] User data may be collected from the user's profile, input from the user, metadata about such information, or a combination thereof. For example, a user may request that the personalization engine collect user data from an existing public-facing profile. An example of direct input may be a user participating in a personalization quiz, and another example of direct input may be the user submitting feedback to the system.

[0036] User data may be used to identify a user's dependencies or preferences. Dependencies may distort rational thought processes and prevent individuals from making sound decisions. Types of an individual's dependencies may include, for example, confirmation bias, anchoring bias, halo effect, availability heuristic, optimism bias, etc. Dependencies may be identified using methods known in the art or methods developed below. In some embodiments, dependencies may be assessed by analyzing historical topics a user has viewed or interacted with; for example, if a user has viewed many posts about a particular topic, this may indicate that the user has dependencies on that particular topic. Identifying a user's dependencies may enable the user to compensate for the identified dependencies, for example, by more critically analyzing information when the identified dependencies are present.

[0037] Identifying data (step 202) may include analyzing post data (step 220). Post data may include post topics 222 and post content 224. A post analysis algorithm may be used to analyze the post topics 222 and post content 224; for example, a latent Dirichlet allocation (LDA) model may be used to evaluate the post topics 222, or the post content 224, or a combination thereof. Other analysis algorithms, such as a latent semantic indexing (LDI) model, may also be used. Post topics 222 may be identified by processing the posts with a trained classifier to classify the posts according to the type of information or keywords they contain. Post content 224 may be identified by processing the posts with a trained classifier to classify the posts according to their content.

[0038] The post topic 222 or the post content 224, or a combination thereof, may be considered post properties, i.e., properties of the post. In some implementations, the properties of the post include the post's title or topic, or a combination thereof, and the post's popularity. The post's popularity may be a measure of the post's virality, such as whether the post has gone viral or the measure of the post's likelihood of becoming viral. The post's popularity may be measured, for example, by how many views or shares, or a combination thereof, the post receives over a certain time span.

[0039] The same trained classifier may be used to analyze both the post topics 222 and the post content 224, or alternatively, different trained classifiers may be used for different components of analyzing the post data (step 220). Trained classifiers may be trained, retrained, and updated to improve the identification or analysis process, or to improve the identification and analysis process. In some embodiments, data collected from user input (e.g., user feedback) may be used to retrain a model to identify or analyze, or identify and analyze, the data.

[0040] Some embodiments may further include analyzing the property, identifying one or more characteristics based on the property, comparing the property to one or more historical properties, and determining that the property meets or exceeds a reputation threshold. In some embodiments, the properties of the post may include the reputation of the post's origin and the factual controversy of the post.

[0041] Process 200 may include determining session metrics (step 230). The session metrics may include navigation patterns. Determining session metrics (step 230) may include evaluating a user's navigation patterns. A user's navigation patterns may include, for example, a user's scrolling speed, clicks over time, the type of posts interacted with (e.g., recordings, images, or articles), the type of content interacted with (e.g., comedy sketches or documentaries), the number of posts interacted with in a given period, and similar information. Determining session metrics (step 230) may include comparing a user's current navigation patterns with the user's navigation history patterns. For example, a user may typically read documentary history articles, and if the user watches a comedy skit, a change in the user's navigation patterns may be detected.

[0042] Some embodiments may include analyzing the interaction with content on a network and evaluating the user's response based on the interaction. For example, user data may indicate that a user averages 10 clicks per minute, and if the user engages in a session averaging 15 clicks per minute, the system may interpret the user's disposition as being in an enthusiastic state. Alternatively, if the user averages 10 clicks per minute, and the user engages in a session averaging 6 clicks per minute, the system may interpret the user's disposition as being in a weary state.

[0043] Process 200 may include inputting data into a model (step 240). The model may be an ML model. In some embodiments, the ML model may be a supervised ML algorithm. The model may integrate session metrics, user data, and posting data. The model may use any of the integrated or available data, or any of the integrated and available data, as input to generate one or more questions for the user, or to generate statements to encourage the user to engage in analytical thinking, or a combination thereof. The model may generate one or more questions for the user, for example, by categorizing the input data into one or more sets of questions and selecting one or more questions from these sets, selecting one or more questions from a list of questions preloaded in a database, generating one or more new questions (e.g., using curated questions and feedback data to evoke additional questions), or some combination thereof.

[0044] Process 200 may include outputting a prompt (step 250). Questions or statements, or a combination thereof, generated by the model to encourage analytical thinking may be output on the prompt for the user to view or engage with, or a combination thereof. Some embodiments may include a user setting to select a type of cue. For example, some users may choose to have the prompt be a visual cue (e.g., a pop-up screen or a tag associated with the post), some users may select an auditory prompt (e.g., a bot may read aloud a question generated by the model), and some users may select a combination thereof (e.g., five questions may be displayed visually and one of the questions is read aloud by a bot).

[0045] The user's state (e.g., whether engrossed or tired) may contribute to one or more of the user's responses, and the system may adapt accordingly. For example, the system may provide fewer questions to a user in a tired state than to a user in an engrossed state. In another example, the system may present simpler questions to a user in a tired state and more complex questions to a user in an engrossed state.

[0046] 3 illustrates a system decision tree 300 according to some embodiments of the present disclosure. The system decision tree 300 may guide the system from a first location (e.g., the location of start step 302), through the system's detections, inputs, and outputs, to a decision completion location (e.g., the location of end step 354), and back to the first location.

[0047] The system may begin step 302 in a dormant or resting state, waiting and monitoring for user activity. The system may detect the user's intent to share a post (step 310). The system may detect whether the user is willing to share the post (step 312), for example, by observing the user press a share button. If the user is not willing to share the post (step 312a), the analysis may terminate step 304 and return the system to its original starting state at step 302.

[0048] If the user is willing to share the post (step 312b), the decision tree and analysis therefor may continue. The system may infer a user profile (step 320) to continue the decision tree. Inferring the user profile may include compiling and evaluating the user's demographic data, historical inputs, and similar information to approximate the user's habits, biases, and other likely characteristics. The system may infer a user profile (step 320) to optimize the personalization of alerts for the user. For example, a first user's profile may indicate that the first user is analytically engaged with questions related to the first user's emotions, and a second user's profile may indicate that the second user is analytically engaged with questions citing numerical data from one or more external sources.

[0049] The system may infer (step 330) the posted information. Inferring the posted information may include evaluating the title, topic, or content of the post, or a combination thereof. The system may use an algorithm (e.g., a post analysis algorithm) to infer (step 330) the posted information. The posted information may be used to evaluate the post's popularity, interest to the user, controversy of the post, and other data.

[0050] The posting information can be used in combination with the user profile to personalize an alert specific to the user. For example, a first user may be inclined to share a post because the post aligns with the first user's views; therefore, the personalized alert can include a question to provoke analytical thinking regarding confirmation bias. In another example, a second user may be inclined to share a post because the post elicits an emotional response; therefore, the personalized alert can include a question regarding the user's reaction.

[0051] The system can then input data into a recommendation model (step 340). The data input into the recommendation model can include user profile data, posted information, user feedback (e.g., user input from one or more previous prompts), and similar information. The recommendation model can be an ML model.

[0052] The system may then recommend (step 350) questions that can be used to prompt the user. The questions may be personalized alerts to the user, taking into account context such as the user's recent reactions, post content, and user history profile data. The recommended questions may be presented to the user to prompt the user to engage in analytical thinking before interacting with or promoting a particular post. For example, a user may read an article, and the system may provide a tag at the end of the article and above an integrated share button. The tag may suggest a question for the user to ponder the content of the post before clicking the share button.

[0053] The system decision tree 300 may terminate (step 354) after recommending one or more questions, and then return to the original starting state (step 302) and may remain dormant until detecting the user's shared intent (step 310), at which point the system decision tree 300 may begin again.

[0054] FIG. 4 illustrates a flowchart diagram (400) for compiling data according to some embodiments of the present disclosure. The system may identify a user (step 410), determine the identified user's session interactions (step 420), input the data into a recommendation model (step 430), recommend questions based on the collected data and the used recommendation model (step 440), and select one or more personalized alerts from a recommendation matrix 450 based on the incorporated data. The recommendation matrix 450 may be used to present the user with personalized alerts that encourage the user to engage in analytical thinking, effectively slowing the spread of information while still allowing the sharing of information and ideas. The present disclosure may thereby enable users' intellectual growth and slow the spread of materially inaccurate information without chilling speech (e.g., by deleting posts by administrators).

[0055] The system may identify the user (step 410) by collecting user profile information, such as user demographics, user interaction history, user interests and interactions, and similar user information. The user may opt in or out of any personalization. For example, a user may indicate that the system may use activity history data for personalization purposes, but may not use geographic location history for the same personalization purposes.

[0056] The system may also identify the user based on additional information provided by the user (step 410). In some embodiments, the system may include the user's response history to identify the user's current response, thereby enhancing personalization. The system may include user feedback to incorporate user preferences, settings, and other data into the user identification. In some embodiments, user feedback may be expressed directly; for example, the user may instruct the system to incorporate certain preferences, or the user may identify that a particular question engaged the user in analytical thinking. In some embodiments, user feedback may be implicit. For example, the system may recognize that some questions result in a five-second pause before the user clicks the share button, but other questions result in only a two-second pause before the user clicks the share button.

[0057] The system may determine the user's session interactions (step 420). The system may aggregate data from previous user sessions and compare the current session to the previous sessions. Session interaction data may include user experience (UX) navigation patterns, such as scrolling speed, clicks over time, and reactions over time. This information may be used, for example, to identify the user's reactions or mood in the current session, or a combination thereof. This information may also be integrated with posting data (e.g., posting topic or content, or a combination thereof), and the system may use, for example, an analysis algorithm (e.g., LDA or LSI) to identify the posting data. The system may further extract features from the user data and posting data based on the contextualized information.

[0058] The user profile data and session information may be aggregated and used as training or other input data for a recommendation model (step 430). The recommendation model may be or may include a classification model, such as a support-vector machine (SVM) model, a logistic regression model, a deep neural network (DNN) model, etc. User data, post data, user interaction data, user response data, post content, or extracted features thereof, or a combination thereof, may be incorporated as training data for the recommendation model.

[0059] The data, whether collected or developed, may be aggregated into recommendation matrix 450. Recommendation matrix 450 may include input data: user data 450a and posted data 450b. User data 450a and posted data 450b may be used to generate output data 450c.

[0060] User data 450a may include information about a user. User data 450a may include user profile data 451 and reaction data 452. User profile data 451 may include information a user may include in a profile, similar identification system, or other information about the user. User profile data 451 may include, for example, user personal information (e.g., geography, education), historical data (e.g., interactions with posts, scrolling speed, reactions to content), interests (e.g., types of content providers followed, content on book wish lists, trends in historical data), etc. User profile data 451 may be maintained for one or more users 451a-451c. Reaction data 452 may include information about moods 452a-452c for each of one or more users 451a-451c.

[0061] Post data 450b may include information about posts that one or more users 451a-451c are considering sharing. Post data 450b may include post topic 453, popularity 454, and accuracy 455. Different posts may have different topics 453a-453c. A post may have more than one topic; for example, a post discussing the best outfit for enjoying pizza may be tagged with both the identifiers "fashion" and "food." Each post may have a popularity rating 454a-454c to indicate whether the post is viral or how likely it is to become viral. Each post may also have an accuracy rating 455a-455c to indicate whether the post is fact or opinion, or how controversial the facts stated in the post are, or a combination thereof.

[0062] Post data 450b may further include information related to popularity 454. Popularity 454 may indicate how many users are currently engaged with the post, how many users previously engaged with the post, how viral the post is currently, how likely the post is to go viral, and similar information. Post popularity 454 may change based on trends, time intervals, days of the week, how popular other posts in similar categories are, etc. Thus, popularity 454 may vary not only from post to post but also based on when a user views the post. Thus, popularity tags 454a-454c may change over time, even for the same post.

[0063] Post data 450b may be normalized. For example, post topic 453 may be selected from a set of topics (e.g., health, current events, fashion, or cooking, or a combination thereof). Numerical identifiers, such as popularity 454 and accuracy 455, may be normalized numerically or on a preset scale. For example, a post's popularity 454 may be numerically normalized from 0 to 1, such that a rating of 0.1 indicates the post has no potential to go viral, while a rating of 0.99 indicates the post is already viral. Similarly, accuracy 455 may use a normalized rating system from 0 to 1, such that a rating of 0.1 indicates the post contradicts reputable sources, a rating of 0.5 indicates the post is unverifiable (e.g., comparable data is unavailable or the post is opinion), and a rating of 0.99 indicates the post is verifiable through multiple reputable sources. A linguistic range may be used for the current scale. For example, popularity ranges may include not viral, unlikely to go viral, potentially viral, almost viral, and currently viral.

[0064] Post data 450b may be maintained for each post available for sharing. For example, the topic 453 of each post may vary, with some posts having several topic tags 453a-453c. The topic tags 453a-453c may be unique to each post. The topic tags 453a-453c may be completely unique, similar, identical, both, or some combination thereof.

[0065] Inputting user data 450a and posted data 450b into recommendation matrix 450 may result in output data 450c. Output data 450c may include question sets 457 developed specifically to engage a particular user in analytical thinking. Question sets 457a-457c may vary based on user data 450a, posted data 450b, and any models used in generating question sets 457a-457c (including model training data). Question sets 457a-457c may then be used to prompt the user with personalized alerts.

[0066] For example, a first set of questions 457a may include: Do you really want something that is likely to be inaccurate? Is the person or organization that created the post aware of their editorial standards? Would you like to verify the information with another source before disseminating it because the post may be consistent with your own views?

[0067] For example, a second set of questions 457b might include: Did this post reinforce any negative feelings? Are you comfortable sharing something that could be perceived as harmful by others? Are you comfortable sharing a post that could encourage unscrupulous behavior?

[0068] For example, a third set of questions 457c might include: Do you consider the source of information to be trustworthy? Are you comfortable sharing something that is likely to be inaccurate? Is the content of the post consistent with the publications of any professional organizations?

[0069] Question sets 457a-457c may be selected from a set of questions curated by experts. The questions may include, for example, whether the user acknowledged the factual controversy of the post; how the post made the user feel; whether the post amplified any particular emotion of the user; whether the user would like to share something with a certain accuracy rating; if the user would like to verify data before sharing the post; whether the user would like to share a post that may contain factually incorrect information; how people the user may influence by spreading the post will react to the post; whether the user considers the post to be credible; whether the user trusts the poster; whether the user believes the content of the post is accurate; whether the facts of the post are consistent with statements by a trusted organization; whether the organization that created the post has specific editorial standards; whether the user experiences confirmation bias; and similar questions.

[0070] Although this disclosure includes detailed descriptions related to cloud computing, it should be understood that implementation of the teachings recited herein is not limited to a cloud computing environment. Rather, embodiments of the present invention can be implemented in conjunction with any other type of computing environment now known or later developed.

[0071] Cloud computing is a service delivery model for enabling convenient, on-demand network access to a shared pool of configurable computing resources (e.g., networks, network bandwidth, servers, processing, memory, storage, applications, virtual machines, and services) that can be rapidly provisioned and released with minimal administrative effort or interaction with the provider of the service. The cloud model can include at least five characteristics, at least three service models, and at least four deployment models.

[0072] The features are as follows:

[0073] On-demand self-service: A cloud consumer can unilaterally provision computing capacity, such as server time and network storage, as needed, without requiring human interaction with the provider of the service.

[0074] Broad network access: Functionality is available over the network and accessed via standard mechanisms that facilitate use by heterogeneous thin or thick client platforms (e.g., mobile phones, laptops, and PDAs).

[0075] Resource Pooling: A provider's computing resources are pooled to serve multiple consumers using a multi-tenant model, and various physical and virtual resources are dynamically allocated and reallocated according to demand. Consumers generally have no control or knowledge of the exact location of the resources provided, but are said to be location-independent in that they may be able to specify a location at a higher level of abstraction (e.g., country, state, or data center).

[0076] Rapid Elasticity: Capabilities can be provisioned quickly and elastically, sometimes automatically, scaled out quickly, released quickly, and scaled in quickly. To the consumer, the capabilities available for provisioning are often unlimited and can be purchased in any quantity at any time.

[0077] Measured Services: Cloud systems automatically control and optimize resource usage by using metering capabilities at some level of abstraction appropriate to the type of service (e.g., storage, processing, bandwidth, and active user accounts). Resource usage can be monitored, controlled, and reported, providing transparency to both providers and consumers of the services being used.

[0078] The service model is as follows:

[0079] Software as a Service (SaaS): The capability offered to consumers to use a provider's applications running on a cloud infrastructure. The applications are accessible from a variety of client devices through a thin-client interface, such as a web browser (e.g., web-based email). The consumer does not manage or control the underlying cloud infrastructure, including the network, servers, operating systems, storage, or even individual application functions, with the possible exception of limited user-specific application configuration settings.

[0080] Platform as a Service (PaaS): The capability offered to consumers to deploy consumer-created or acquired applications, created using programming languages ​​and tools supported by the provider, onto a cloud infrastructure. The consumer does not manage or control the underlying cloud infrastructure (e.g., including networks, servers, operating systems, or storage), but does have control over the deployed applications and, in some cases, the application-hosting environment configuration.

[0081] Infrastructure as a Service (IaaS): The capability offered to consumers to provision processing, storage, network, and other basic computing resources on which they can deploy and run any software, which may include operating systems and applications. The consumer does not manage or control the underlying cloud infrastructure, but does have control over the operating systems, storage, deployed applications, and in some cases, limited control over selecting network components (e.g., host firewalls).

[0082] The deployment models are as follows:

[0083] Private Cloud: Cloud infrastructure is operated exclusively for an organization. The cloud infrastructure may be managed by the organization or a third party, and may reside on-premises or off-premises.

[0084] Community Cloud: Cloud infrastructure is shared by several organizations and supports a specific community with common interests (e.g., mission, security requirements, policies, and compliance considerations). The cloud infrastructure may be managed by the organizations or a third party and may reside on-premises or off-premises.

[0085] Public Cloud: Cloud infrastructure is available to the general public or large industry groups and is owned by organizations that sell cloud services.

[0086] Hybrid Cloud: A cloud infrastructure is a blend of two or more clouds (private, community, or public) that remain unique entities but are brought together by standardized or proprietary technologies (e.g., cloud bursting for load balancing between clouds) that enable data and application portability.

[0087] A cloud computing environment is service oriented with a focus on statelessness, low coupling, modularity, and semantic interoperability. At the heart of cloud computing is an infrastructure comprising a network of interconnected nodes.

[0088] 5 illustrates a cloud computing environment 510 according to an embodiment of the present disclosure. As illustrated, the cloud computing environment 510 includes one or more cloud computing nodes 500, with which local computing devices used by cloud consumers, such as a personal digital assistant (PDA) or mobile phone 500A, a desktop computer 500B, a laptop computer 500C, or an automotive computer system 500N, or any combination thereof, may communicate. The nodes 500 may communicate with each other. The nodes 500 may be physically or virtually grouped into one or more networks (not shown), such as a private cloud, a community cloud, a public cloud, or a hybrid cloud, as described herein above, or any combination thereof.

[0089] This allows the cloud computing environment 510 to provide infrastructure, platform, or software, or a combination thereof, as a service without the cloud consumer having to maintain resources on a local computing device. It is understood that the types of computing devices 500A-500N shown in Figure 5 are intended to be exemplary only, and that the cloud computing node 500 and the cloud computing environment 510 can communicate with any type of computerized device (e.g., using a web browser) over any type of network or network-addressable connection, or combination thereof.

[0090] 6 illustrates abstraction model layers 600 provided by cloud computing environment 510 (of FIG. 5) according to an embodiment of the present disclosure. It should be understood that the components, layers, and functions illustrated in FIG. 6 are intended to be merely exemplary, and that embodiments of the present disclosure are not limited thereto. As shown, the following layers and corresponding functions are provided:

[0091] The hardware and software layer 615 includes hardware and software components. Examples of hardware components include a mainframe 602, a RISC (Reduced Instruction Set Computer) architecture-based server 604, a server 606, a blade server 608, a storage device 611, and a network and networking component 612. In some embodiments, software components include network application server software 614 and database software 616.

[0092] The virtualization layer 620 provides an abstraction layer from which the following examples of virtual entities can be provided: virtual servers 622; virtual storage 624; virtual networks 626, including, for example, virtual private networks; virtual applications and operating systems 628; and virtual clients 630.

[0093] In one example, management layer 640 may provide several functions, as described below. Resource provisioning 642 provides dynamic procurement of computing and other resources used to execute tasks within the cloud computing environment. Metering and pricing 644 provides cost tracking as resources are utilized within the cloud computing environment and billing or invoicing for the consumption of these resources. In one example, these resources may include application software licenses. Security provides identity verification for cloud consumers and tasks and protection for data and other resources. User portal 646 provides access to the cloud computing environment for consumers and system administrators. Service level management 648 provides allocation and management of cloud computing resources so that required service levels are met. Service level agreement (SLA) planning and fulfillment 650 provides pre-allocation and procurement of cloud computing resources where future requirements are predicted according to SLAs.

[0094] Workload tier 660 provides examples of functions for which a cloud computing environment may be utilized. Examples of workloads and functions that may be provided from this tier include one of: mapping and navigation 662; software development and lifecycle management 664; virtual classroom instructional delivery 667; data analytics processing 668; transaction processing 670; and personalized alerts to engage analytical thinking 672.

[0095] Although this disclosure includes detailed descriptions of cloud computing, it should be understood that implementation of the teachings described herein is not limited to cloud computing environments. Rather, embodiments of the present invention can be implemented in conjunction with any other type of computing environment now known or later developed.

[0096] 7 illustrates a high-level block diagram of an exemplary computer system 701 that may be used to implement (e.g., using one or more processor circuits of a computer or computer processor) one or more of the methods, tools, and modules described herein, and any associated functionality, in accordance with embodiments of the present disclosure. In some embodiments, the major components of computer system 701 include a processor 702 having one or more central processing units (CPUs) 702A, 702B, 702C, and 702D, a memory subsystem 704, a terminal interface 712, a storage interface 716, an I / O (input / output) device interface 714, and a network interface 718, all of which may be communicatively coupled, directly or indirectly, for communication between components via a memory bus 703, an I / O bus 708, and an I / O bus interface unit 710.

[0097] Computer system 701 may include one or more general-purpose programmable CPUs 702A, 702B, 702C, and 702D (generically referred to herein as CPUs 702). In some embodiments, computer system 701 may include multiple processors typical of relatively large systems, although in other embodiments, computer system 701 may alternatively be a single CPU system. Each CPU 702 may execute instructions stored in memory subsystem 704 and may include one or more levels of on-board cache.

[0098] System memory 704 may include computer system-readable media in the form of volatile memory, such as random access memory (RAM) 722 or cache memory 724. Computer system 701 may also include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 726 may be provided for reading from and writing to non-removable, non-volatile magnetic media, such as a “hard drive.” Although not shown, a magnetic disk drive may be provided for reading from and writing to a removable, non-volatile magnetic disk (e.g., a “floppy disk”), or an optical disk drive may be provided for reading from and writing to a removable, non-volatile optical disk, such as a CD-ROM, DVD-ROM, or other optical media. Additionally, memory 704 may include flash memory, such as a flash memory stick drive or flash drive. Memory devices may be connected to memory bus 703 by one or more data media interfaces. Memory 704 may include at least one program product having a set (eg, at least one) of program modules configured to perform the functions of various embodiments.

[0099] One or more programs / utilities 728 (each having at least one set of program modules 730) may be stored in memory 704. The programs / utilities 728 may include a hypervisor (also referred to as a virtual machine monitor), one or more operating systems, one or more application programs, other program modules, and program data. Each of the one or more operating systems, one or more application programs, other program modules, and program data, or some combination thereof, may comprise an implementation of a network environment. The programs 728 or program modules 730, or a combination thereof, generally perform the functions or methodologies of various embodiments.

[0100] 7 as a single bus structure providing a direct communication path between CPU 702, memory subsystem 704, and I / O bus interface 710, memory bus 703, in some embodiments, may include multiple distinct buses or communication paths, which may be arranged in any of a variety of configurations, such as point-to-point links in a hierarchical, star, or web configuration; multiple hierarchical buses; parallel and redundant paths; or any other suitable type of configuration. Moreover, while I / O bus interface 710 and I / O bus 708 are shown as separate units, computer system 701, in some embodiments, may include multiple I / O bus interface units 710, multiple I / O buses 708, or both. Furthermore, while multiple I / O bus interface units 710 are shown isolating I / O bus 708 from the various communication paths running to various I / O devices, in other embodiments, some or all of the I / O devices may be directly connected to one or more system I / O buses 708.

[0101] In some embodiments, computer system 701 may be a multi-user mainframe computer system, a single-user system, a server computer, or a similar device that has little or no direct user interface but receives requests from other computer systems (clients). Further, in some embodiments, computer system 701 may be implemented as a desktop computer, a portable computer, a laptop or notebook computer, a tablet computer, a pocket computer, a telephone, a smartphone, a network switch or router, or any other suitable type of electronic device.

[0102] It should be noted that Figure 7 is intended to illustrate representative major components of an exemplary computer system 701. However, in some embodiments, the individual components may be more or less complex than depicted in Figure 7, there may be components other than or in addition to those depicted in Figure 7, and the number, type, and configuration of such components may vary.

[0103] The present invention may be a system, method, computer program product, or computer program, or any combination thereof, at any level of technical detail that may be integrated. The computer program product may include one or more computer-readable storage media having computer-readable program instructions for causing a processor to perform aspects of the present invention.

[0104] The computer-readable storage medium can be a tangible device capable of holding and storing instructions for use by an instruction execution device. The computer-readable storage medium can be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. A non-exhaustive list of more specific examples of the computer-readable storage medium includes the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as a punch card or a ridge structure in a groove in which instructions are stored, or any suitable combination thereof. As used herein, a computer-readable storage medium should not be construed as a transitory signal per se, such as an electric wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse passing through a fiber optic cable), or an electrical signal transmitted over an electrical wire.

[0105] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to an individual computing device / processing device, or to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, or a wireless network, or a combination thereof. The network may be comprised of copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, or edge servers, or a combination thereof. A network adapter card or network interface in each computing device / processing device receives the computer-readable program instructions from the network and transfers the computer-readable program instructions to the individual computing device / processing device for storage in a computer-readable storage medium.

[0106] The computer-readable program instructions for carrying out the operations of the present invention may be either assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, configuration data for an integrated circuit, or source or object code written in any combination of one or more programming languages, such as object-oriented programming languages, e.g., Smalltalk, C++, etc., or conventional procedural programming languages ​​(e.g., the "C" programming language or similar programming languages). The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, partially on the user's computer as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer via any kind of network, such as a local area network (LAN) or a wide area network (WAN), or the connection may be to an external computer (e.g., over the Internet using an Internet Service Provider). In some embodiments, electronic circuits, such as programmable logic circuits, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), may execute computer-readable program instructions by utilizing state information of the computer-readable program instructions to personalize the electronic circuitry to perform aspects of the invention.

[0107] Aspects of the present invention are described herein with reference to flowchart illustrations or block diagrams, or combinations thereof, of methods, apparatus (systems), and computer program products or computer programs according to embodiments of the invention. It will be understood that each block of the flowchart illustrations or block diagrams, or combinations thereof, and combinations of blocks in the flowchart illustrations or block diagrams, or combinations thereof, can be implemented by computer-readable program instructions.

[0108] These computer-readable program instructions may be provided to a processor of a computer or other programmable data processing apparatus, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in one or more blocks of the flowchart diagrams or the block diagrams, or a combination thereof, to produce a machine. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer-programmable data processing apparatus or other device, or a combination thereof, to function in a particular manner, such that a computer-readable storage medium having stored instructions includes an article of manufacture including instructions that implement aspects of the functions / acts specified in one or more blocks of the flowchart diagrams or the block diagrams, or a combination thereof.

[0109] The computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device such that the instructions, which execute on the computer, other programmable data processing apparatus, or other device, implement the functions / acts identified in one or more blocks of the flowchart diagrams or block diagrams, or a combination thereof, to cause the computer, other programmable apparatus, or other device to perform a series of operating steps to generate a computer-implemented process.

[0110] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products or computer programs according to various embodiments of the present invention. In this regard, each block in the flowcharts or block diagrams may represent a module, segment, or portion of instructions, which includes one or more executable instructions for implementing one or more specified logical functions. In some alternative implementations, the functions shown in the blocks may occur out of the order shown in the figures. For example, two blocks shown in succession may actually be accomplished as a single step performed simultaneously, substantially simultaneously, partially, or fully in a time-overlapping manner, depending on the functionality involved, or the blocks may be performed in the reverse order. It should be noted that each block of the block diagrams or flowchart diagrams or combinations thereof, and combinations of multiple blocks in the block diagrams or flowchart diagrams or combinations thereof, may be implemented by a special-purpose hardware-based system that performs the specified functions or operations, or may execute a combination of special-purpose hardware and computer instructions.

[0111] While the present disclosure has been described with reference to particular embodiments, it is expected that variations and modifications thereof will be apparent to those skilled in the art. The description of various embodiments of the present invention has been presented for illustrative purposes and is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terms used in this specification have been selected to best explain the principles of the embodiments, practical applications, or technical improvements over technology found in the marketplace, or to enable those skilled in the art to understand the embodiments disclosed herein. It is therefore intended that the appended claims be construed to embrace all such modifications and variations that fall within the true spirit and scope of the present disclosure.

Claims

1. 1. A system comprising: memory; and a processor in communication with the memory wherein the processor: Analyzing interactions by a user in the network; generating a user profile for said user; Identifying attempts by the user to share posts over the network; and Prompting the user with a personalized alert to rate the post. configured to perform operations including wherein the personalized alert is generated based on the interaction, the user profile, and properties of the post; wherein the interactions and the user profile are user data contained in a corpus; the properties of the posts are included in the corpus; a machine learning algorithm trained on the corpus as input and personalized alerts as output; and generating the personalized alert by inputting the interaction, the user profile, and properties of the post into the trained machine learning algorithm, and outputting the personalized alert from the trained machine learning algorithm; The system.

2. defining the user profile, Evaluating how the user interacts with the network 2. The system of claim 1, wherein said evaluating considers a scrolling speed of the user, an amount of interaction of the user with content on the network, and a time between multiple interactions of the user with the content on the network.

3. The system described in claim 1, wherein the machine learning algorithm is a supervised machine learning model.

4. receiving feedback from said user; and Integrating said feedback into said corpus. The system of claim 3 further comprising:

5. analyzing the interactions with content on the network; and Evaluating a response of the user based on the interaction. The system of claim 1 further comprising:

6. the properties of the post include the topic of the post and the popularity of the post; The system of claim 1 .

7. analyzing said property; identifying one or more characteristics based on said properties; comparing the property to one or more historical properties; and determining that the property is above a reputation threshold; The system of claim 1 further comprising:

8. 1. A computer-implemented method comprising: analyzing, by a processor, interactions by a user in the network; generating, by the processor, a user profile for the user; Identifying, by the processor, an attempt by the user to share a post over the network; and prompting, by the processor, the user with a personalized alert to rate the post. Including, wherein the personalized alert is generated based on the interaction, the user profile, and properties of the post; wherein the interactions and the user profile are user data contained in a corpus; the properties of the posts are included in the corpus; a machine learning algorithm trained on the corpus as input and personalized alerts as output; and generating the personalized alert by inputting the interaction, the user profile, and properties of the post into the trained machine learning algorithm, and outputting the personalized alert from the trained machine learning algorithm; The method.

9. defining the user profile, evaluating, by the processor, how the user interacts with the network.

9. The method of claim 8, wherein said evaluating considers a scrolling speed of the user, an amount of interaction of the user with content on the network, and a time between multiple interactions of the user with the content on the network.

10. The method of claim 8, wherein the machine learning algorithm is a supervised machine learning model.

11. receiving feedback from the user by the processor; and Integrating the feedback into the corpus by the processor. The method of claim 10 further comprising:

12. analyzing, by the processor, the interactions with content on the network; and evaluating, by the processor, a response of the user based on the interaction. The method of claim 8 further comprising:

13. the properties of the post include the topic of the post and the popularity of the post; The method of claim 8.

14. analyzing said property; identifying one or more characteristics based on said properties; comparing the property to one or more historical properties; and determining that the property is above a reputation threshold; The method of claim 8 further comprising:

15. A computer program comprising: Analyzing interactions by a user in the network; generating a user profile for said user; Identifying attempts by the user to share posts over the network; and prompting the user to rate the post with a personalized alert, wherein the personalized alert is generated based on the interaction, the user profile, and properties of the post; causing a processor to execute each step of the method, including wherein the interactions and the user profile are user data contained in a corpus; the properties of the posts are included in the corpus; a machine learning algorithm trained on the corpus as input and personalized alerts as output; and generating the personalized alert by inputting the interaction, the user profile, and properties of the post into the trained machine learning algorithm, and outputting the personalized alert from the trained machine learning algorithm; The computer program.

16. analyzing said property; identifying one or more characteristics based on said properties; comparing the property to one or more historical properties; and determining that the property is above a reputation threshold; The computer program product of claim 15 , further comprising causing the processor to execute:

17. defining the user profile, Evaluating how the user interacts with the network 16. The computer program product of claim 15, wherein said evaluating takes into account a scrolling speed of the user, an amount of interaction of the user with content on the network, and a time between multiple interactions of the user with the content on the network.

18. The computer program of claim 15, wherein the machine learning algorithm is a supervised machine learning model.

19. receiving feedback from said user; and Integrating said feedback into said corpus.

20. The computer program product of claim 18, further comprising causing the processor to execute:

20. analyzing the interactions with content on the network; and Evaluating a response of the user based on the interaction. The computer program product of claim 15 , further comprising causing the processor to execute:

Images