System and method for sentiment analysis based interactive engagement using machine learning

Abstract

An integrated system (106) for sentiment analysis using machine learning. The system (106) receives data associated with one or more users, where the data comprises one or more parameters associated with interaction among the one or 5 more users during a predefined schedule. The system (106) analyzes, the one or more parameters to determine one or more sentiments associated with the one or more users. The system (106) dynamically configures, via a machine learning engine (214), the predefined schedule based on the determined one or more sentiments. The system (106) enables, interaction among the one or more users 10 using the dynamically configured predefined schedule.

Description

[0001] SYSTEM AND METHOD FOR SENTIMENT ANALYSIS BASED INTERACTIVE ENGAGEMENT USING MACHINE LEARNING

[0002] FIELD OF THE INVENTION

[0003]

[0001] The present disclosure relates to the field of an interactive content delivery and interactive engagement platforms. More specifically, the present disclosure provides a system and method for sentiment analysis-based interaction using machine learning.

[0004] BACKGROUND OF THE INVENTION

[0005]

[0002] With the increasing adoption of interactive systems across diverse environments such as virtual workplaces, educational platforms, and fitness settings, ensuring effective, inclusive, and engaging interactions among users remains a significant challenge. Existing systems often rely on static or preconfigured interaction frameworks that fail to adapt dynamically to the real-time emotional and behavioural states of participants. This limitation leads to diminished engagement, unaddressed user conflicts, and suboptimal outcomes, particularly in settings where collaboration or personalized experiences are critical.

[0006]

[0003] A key technical problem arises from the inability to process and analyze real-time multimodal data — such as voice, text, and behavioural metrics — at scale, to infer user sentiments accurately and adapt interactions dynamically. Current approaches to sentiment analysis often focus on single-modal data (e.g., text or voice) and lack the sophistication to integrate insights from multiple sources in real-time. This limitation restricts the system's ability to provide meaningful feedback or adjust interaction parameters dynamically, which is crucial in environments with varying user preferences and emotional states.

[0007]

[0004] Another challenge lies in managing conflicts during group interactions. Traditional systems lack mechanisms to detect and mediate conflicts arising from emotional or behavioural mismatches among users. This oversight often leads to reduced collaboration, disengagement, and, in some cases, negative outcomes for the group as a whole.

[0005] In addition, systems that attempt to address user engagement often depend on predefined schedules or activity plans that are not adaptable to evolving group dynamics. For example, in group fitness settings, participants with different energy levels or emotional states may require tailored activities to maintain motivation and inclusivity, which current systems are unable to provide effectively.

[0008]

[0006] Finally, real-time feedback collection and iterative activity adjustment remain underdeveloped in many existing solutions. While feedback mechanisms exist, they are often reactive rather than proactive, and the lack of integration with dynamic machine learning techniques further hinders their effectiveness.

[0009]

[0007] Therefore, there is a need for a method and system that addresses the above-mentioned technical problems by providing a solution which impacts user experience and user interaction.

[0010] SUMMARY

[0011]

[0008] The present disclosure relates to the field of an interactive content delivery and interactive engagement platforms. More specifically, the present disclosure provides a system and method for sentiment analysis-based interaction using machine learning.

[0012]

[0009] This invention addresses these technical challenges by providing a dynamic, sentiment-driven interaction system that leverages advanced machine learning (ML) and artificial intelligence (Al) techniques to analyze multimodal data, detect emotional triggers, adapt schedules, mediate conflicts, and continuously optimize interactions. The result is a robust and scalable solution that ensures personalized, inclusive, and engaging interactions tailored to the needs of diverse users in real-time.

[0013]

[0010] The system and method for sentiment analysis of users using machine learning (ML) for enabling interaction is provided. The present disclosure describes an integrated system for sentiment analysis. The system includes a processor and a memory operatively coupled with the processor, where said memory stores instructions which, when executed by the processor, cause the processor to receive data associated with one or more users, where the datacomprises one or more parameters associated with a live interaction among the one or more users. The processor analyzes the one or more parameters of the live interaction to determine one or more sentiments associated with the one or more users involved in the live interaction. The processor dynamically configures, via a machine learning engine, a schedule based on the one or more determined sentiments. The processor enables interaction among the one or more users as per the dynamically configured schedule.

[0014] DEFINITIONS

[0015] [Oil] The term “integrated system” refers to a framework or platform that facilitates communication, collaboration, and engagement among individuals or groups using a combination of tools, technologies, and interfaces. These systems are designed to streamline social interactions, making it easier for people to connect, share information, and collaborate across different media (e.g., text, voice, video, and social media). The integrated system for social interaction combines various tools, platforms, and technologies to enhance communication, collaboration, and engagement across different channels, both in personal and professional contexts. These systems enable users to interact more effectively in a variety of ways, from simple messaging to immersive virtual experiences.

[0016]

[0012] The term “activities” refers to posting and sharing of photos, videos, status updates, and articles on platforms. Further, activities include engaging with others content by liking, commenting, sharing posts to spark conversations including private conversations between users on platforms. Activities also include streaming live videos and interacting with multiple users via comments or reactions on platforms. Activities include temporary posts where users share moments through photos or videos that disappear a predetermined period. Activities include participating in forums related to specific games for advice, socializing, or organizing events. This may further include engaging in competitive online gaming events where players / users interact with each other, either as teammates or opponents. Activities include collaborating with others in real-time on projects, sharing files, or discussing work-related topics in channels or private messages. Activities include collaborating with others bysimultaneously editing documents, spreadsheets, and presentations in real-time. Activities include working together with teams on projects by organizing tasks and providing feedback within the platform.

[0017]

[0013] The term “sentiment analysis” is the process of determining the emotional tone or sentiment expressed by various users of an application.

[0018]

[0014] The term “emotional triggers” are events, stimuli, or experiences that evoke strong emotional reactions in a person. These triggers can bring up positive or negative feelings, memories, or thoughts, and they can occur consciously or unconsciously. Emotional triggers can vary widely from person to person, depending on their background, experiences, and personality

[0019] BRIEF DESCRIPTION OF DRAWINGS

[0020]

[0015] FIG. 1 illustrates an example system architecture of a proposed system, in accordance with an example embodiment; FIG. 2 illustrates an example block diagram of a proposed system, in accordance with an example embodiment; FIG.

[0021] 3 illustrates a flow diagram of an example method implemented by the proposed system, in accordance with an example embodiment; FIG. 4 illustrates an example block diagram representing user types and functionalities of the proposed system, in accordance with an example embodiment; FIG. 5 illustrates an example block diagram representing various modules implemented by the proposed system, in accordance with an example embodiment; FIG. 6A and 6B illustrate example interfaces implemented by the proposed system, in accordance with an example embodiment.

[0022] DETAILED DESCRIPTION

[0023]

[0016] The system and method for sentiment analysis of users using machine learning (ML) is provided. The present disclosure describes social interaction among users using ML, which involves leveraging algorithms and data-driven techniques to enhance how people connect, communicate, and engage within digital environments. ML can be applied in various ways to improve social interactions, both in user interfaces and in content recommendation systems. The system receives data associated with one or more users, wherein the data comprises one or more parameters associated with a live interaction among theone or more users. The system analyzes the one or more parameters of the live interaction to determine one or more sentiments associated with the one or more users involved in the live interaction. Further, the system dynamically configures, via a machine learning engine, a schedule based on the one or more determined sentiments. The system enables interactions among the one or more users as per the dynamically configured schedule.

[0024]

[0017] Embodiments of the present disclosure may provide a system and a method for sentiment analysis of users using machine learning (ML). The system and the method are described with reference to FIGs. 1 to 6B.

[0025]

[0018] FIG. 1 illustrates example system architecture 100 of the proposed system 106, in accordance with an example embodiment. The system 106 may be connected to one or more user equipments (102-1, 102-2... 102-N) through a network 104. A person of ordinary skill in the art will understand that the one or more user equipments (102-1, 102-2... 102-N) may be collectively referred as the user equipments 102 and individually referred as the user equipment 102. One or more users may access the system 106 through the UEs 102.

[0026]

[0019] The communication network 104 may be wired, wireless, or a combination of both, including cellular, Wi-Fi, internet, or local area networks. It may comprise data, wireless, or telephony networks, such as LAN, MAN, WAN, public networks (e.g., the Internet), or proprietary networks like cable or fiberoptic systems. The network can include nodes capable of transmitting, receiving, processing, or routing data in various forms, such as messages, packets, or signals.

[0027]

[0020] In one example embodiment, the system 106 receives data associated with one or more users through the UEs 102. The one or more users may access the system 106 for engaging in various activities with at least a user among the one or more users.

[0028]

[0021] In one example embodiment, the data may include one or more parameters associated with interaction among the one or more users during a predefined schedule. The one or more parameters comprise at least one of a textbased interaction parameter associated with the one or more users, a voice-based interaction parameter associated with the one or more users, and one or morebehavioural data associated with the one or more users during the one or more interactions.

[0029]

[0022] In one example embodiment, the system 106 analyzes the one or more parameters to determine one or more sentiments associated with the one or more users.

[0030]

[0023] In one example embodiment, the system 106 dynamically configures, via a machine learning engine, a schedule based on the one or more determined sentiments. The schedule is a predefined schedule, and to dynamically configure the predefined schedule, the system 106 analyzes, by the machine learning engine or an artificial intelligence (Al) technique, the one or more sentiments of a plurality of users of the one or more users. The schedule is a predefined schedule, and to dynamically configure the predefined schedule, the system 106 determines, one or more emotional triggers associated with the plurality of users during the interaction based on the one or more sentiments. To dynamically configure the predefined schedule, the system 106 generates, one or more activities to engage the plurality of users during the interaction based on the one or more emotional triggers.

[0031]

[0024] In one example embodiment, the system 106 enables, interaction among the one or more users using the dynamically configured predefined schedule. To enable interaction among the one or more users, the system 106 is configured to record, the one or more emotional triggers among the plurality of users during the one or more activities. To enable interaction among the one or more users, the system 106 is configured to receive feedback associated with the one or more activities from the plurality of users. To enable interaction among the one or more users, the system 106 is configured to vary the one or more activities during the predefined schedule based on the recorded one or more emotional triggers and the received feedback. To enable interaction among the one or more users, the system 106 is configured to enable the interaction among the plurality of users during varied one or more activities for a predetermined period.

[0032]

[0025] In one example embodiment, to receive feedback, the system 106 is configured to receive, on or more real-time inputs from the plurality of usersduring the one or more activities. In response to a determination of one or more conflicts based on the one or more real-time inputs, the system 106 is configured to facilitate one or more discussions among the plurality of users to mediate the one or more conflicts generated during the one or more activities.

[0033]

[0026] In one example embodiment, the system 106 may allow the users to enter their email and password for accessing the activity. The users may enter their registered email address and password associated with their community connectivity platform account. The system 106 may also offer an OTP (One-Time Password) option for password recovery. When users select this method, they will receive a unique OTP on their registered mobile number or email address. After verifying the OTP, users may proceed to reset their password and regain access to their account.

[0034]

[0027] For example, in one embodiment, by integrating geo -location among the predetermined location, the system 106 enables users to discover and access nearby facilities conveniently. Customers / Users registered with the system 106 may effortlessly, match make, schedule appointments, online sessions, webinars, classes, or events and make secure payments directly. Additionally, the system 106 facilitates real-time communication between facility managers, staff, coaches and community members, fostering better engagement and enhancing the overall user experience. Users may receive updates, announcements, and personalized notifications based on their preferences and interests, creating a dynamic and interactive ecosystem. The system 106 may allow the users to select the desired date, time, location, and specify preferences regarding gender, skill level, and fitness goals. Users may choose a date, time, and location for their desired in-person session. Users may also specify preferences such as the gender of their partner, skill level, images filters, and fitness goals. By applying these filters, users may narrow down their search and find potential partners who align with their specific criteria. This streamlined experience allows users to explore potential matches without filtering through specific preferences, making it easier to connect with compatible partners based on other shared interests and values. Further, the system 106 enables a personalized interaction feature that enablesusers, once matched, to send training, health, or social requests to each other. The recipient has the choice to accept or decline the request, and if accepted, they may seamlessly integrate it into their current mobile or tablet calendar. This streamlined process enhances user convenience, fostering effective communication and coordination.

[0035]

[0028] For example, in one embodiment, the system 106 may provide access to content related to wellbeing, comprising blogs, videos, and posts, may offer a variety of resources to help individuals improve their physical, mental, and emotional health. These platforms typically cover topics such as mindfulness, stress management, fitness, nutrition, self-care, mental health, and personal growth. The system 106 enables users to access, interact with, and share wellbeing-related content, engage with other users through likes, shares, and comments, and communicate with specialists through messaging.

[0036]

[0029] For example, in one embodiment, the system 106 may comprise a login interface which comprises fields for users to enter their email and password, along with buttons and features to facilitate account access. Further, the login interface may comprise a “Forgot Password” link or button and also offer an OTP (One-Time Password) option for password recovery. When users select this option, they will receive a unique OTP on their registered mobile number or email address. After verifying the OTP, users may proceed to reset their password and regain access to their account. If users forget their password, they may click on the “Forgot Password” link or button. This action will redirect them to a password recovery interface, where they may provide their registered email address. Further, the system 106 may comprise a password recovery interface that allows users to recover or reset their password when they forget their password or need to update the password for security reasons. This interface typically involves a series of steps to ensure identity verification and provides a secure way to reset or retrieve the password.

[0037]

[0030] For example, in one embodiment, the system 106 may comprise a social media feed interface where users may share and view posts related to exercises, recipes, playlists, music, and other fitness or health-related content. Thesystem 106 may enable clean, user-friendly, and interactive layout that encourages engagement. The system 106 may implement user accounts, post storage, and media hosting. Cloud storage solutions may be used for storing user-generated content (images, videos). The system 106 may further store user profiles, post metadata, interactions (likes, comments, shares). The system 106 may use technologies to provide real-time updates (new posts, comments, likes). The system 106 may ensure proper data encryption and content moderation for a safe and positive user experience.

[0038]

[0031] In one embodiment, the system 106 comprises a processor 202 and a memory 204, as shown in FIG. 2. The memory 204 includes various types of computer-readable storage, such as RAM, ROM, CMOS, HDD, flash memory, and other volatile and non-volatile media, for storing data, instructions, and applications. The processor 202, which can include a CPU, GPU, ASIC, DSP, or other hardware, retrieves and executes instructions stored in the memory to perform operations. It may feature multi-core configurations for parallel processing, support for big data analysis, and pipelined or multithreaded execution.

[0039]

[0032] The memory 204 buffers input data and stores non-transitory instructions enabling the system to execute specified functions. FIG. 2 depicts a block diagram of system 106, where the processor fetches and executes instructions to manipulate data or interact with network services. The system also includes interface(s) 206 for communication with external devices and servers, facilitating data input, output, and interaction with peripherals like keyboards, printers, and storage devices. The interface supports graphical input, real-time data communication, and integration with system components such as processing engines and databases.

[0040]

[0033] The processing engine(s) 208, implemented through hardware and programming, execute specific functionalities using instructions stored in non-transitory media. These engines include a data ingestion engine 212, a machine learning (ML) engine 214, feature extraction engine 216, and support vector machine (SVM) engine 218, along with a database 210 to store or generate datafrom operations. Together, these components enable efficient execution of system functions with scalability and adaptability to user requirements.

[0041]

[0034] In an embodiment, the processor 202 receives data through the data ingestion engine 212. The data may be associated with the users. Further, the processor 202 records the information in the database 210. The one or more users may access the system 106 for engaging in various activities with at least a user among the one or more users.

[0042]

[0035] In an embodiment, the data may include one or more parameters associated with interaction among the one or more users during a predefined schedule. The processor 202 may use the feature extraction engine 216 to extract the one or more parameters from the data. The one or more parameters comprise at least one of a text-based interaction parameter associated with the one or more users, a voice-based interaction parameter associated with the one or more users, and one or more behavioural data associated with the one or more users during the one or more interactions.

[0043]

[0036] In an, the processor 202 analyzes the one or more parameters to determine one or more sentiments associated with the one or more users using the Support Vector Machine (SVM) engine 218.

[0044]

[0037] In an embodiment, based on the data (which may include text), the SVM engine 218 may label the data (e.g., social media posts) where the sentiment (positive / negative) may be annotated. This process may include removing stop words, punctuation, and irrelevant characters from the text. Further, the SVM engine 218 may evaluate the importance of each word in the text based on how frequently it appears in the document and how rare it is across all documents. The SVM engine 218 may split the data into training and testing sets. A SVM model may be trained. After training the model, the model may be deployed to determine one or more sentiments associated with the one or more users.

[0045]

[0038] In one example embodiment, the processor 202 dynamically configures, via a machine learning engine 214, the schedule based on the determined one or more sentiments. To dynamically configure the schedule, the processor 202 analyzes, by the machine learning engine 214 or an artificialintelligence (Al) technique, the one or more sentiments of a plurality of users of the one or more users. The schedule is a predefined schedule, and to dynamically configure the schedule, the processor 202 determines, one or more emotional triggers associated with the plurality of users during the interaction based on the one or more sentiments. To dynamically configure the predefined schedule, the processor 202 generates, one or more activities to engage the plurality of users during the interaction based on the one or more emotional triggers.

[0046]

[0039] In one example embodiment, the processor 202 enables, interaction among the one or more users using the dynamically configured predefined schedule. To enable interaction among the one or more users, the processor 202 is configured to record, the one or more emotional triggers among the plurality of users during the one or more activities. To enable interaction among the one or more users, the processor 202 is configured to receive feedback associated with the one or more activities from the plurality of users. To enable interaction among the one or more users, the processor 202 is configured to vary the one or more activities during the predefined schedule based on the recorded one or more emotional triggers and the received feedback. To enable interaction among the one or more users, the system 106 is configured to enable the interaction among the plurality of users during varied one or more activities for a predetermined period.

[0047]

[0040] In one example embodiment, to receive feedback, the processor 202 is configured to receive, on or more real-time inputs from the plurality of users during the one or more activities. In response to a determination of one or more conflicts based on the one or more real-time inputs, the processor 202 is configured to facilitate one or more discussions among the plurality of users to mediate the one or more conflicts generated during the one or more activities.

[0048]

[0041] FIG. 3 illustrates a flow diagram 300 of the method implemented by the proposed system 106, in accordance with an example embodiment. It will be understood that each block of the flow diagram of the method 300 may be implemented by various means, such as hardware, firmware, processor, circuitry, and / or other communication devices associated with execution of softwarecomprising one or more computer program instructions. For example, one or more of the procedures described above may be embodied by computer program instructions. In this regard, the computer program instructions which embody the procedures described above may be stored by a memory 204 of the system 106, employing an embodiment of the present disclosure and executed by a processor 202 of the system 106.

[0049]

[0042] As will be appreciated, any such computer program instructions may be loaded onto a computer or other programmable apparatus (for example, hardware) to produce a machine, such that the resulting computer or other programmable apparatus implements the functions specified in the flow diagram blocks. These computer program instructions may also be stored in a computer-readable memory that may direct a computer or other programmable apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture the execution of which implements the function specified in the flowchart blocks. The computer program instructions may also be loaded onto a computer or other programmable apparatus to cause a series of operations to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide operations for implementing the functions specified in the flow diagram blocks. Accordingly, blocks of the flow diagram support combinations of means for performing the specified functions and combinations of operations for performing the specified functions for performing the specified functions. It will also be understood that one or more blocks of the flow diagram, and combinations of blocks in the flow diagram, may be implemented by special purpose hardwarebased computer systems which perform the specified functions, or combinations of special purpose hardware and computer instructions

[0050]

[0043] The method 300 is implemented by the system architecture 200. At step 302, method 300 comprises the steps of receiving, by a system 106, data associated with one or more users, wherein the data comprises one or more parameters associated with a live interaction among the one or more users.

[0044] At step 304, method 300 further comprises the steps of analyzing, by the system 106, the one or more parameters of the live interaction to determine one or more sentiments associated with the one or more users involved in the live interaction.

[0051]

[0045] At step 306, method 300 comprises the steps of dynamically configuring, via a machine learning engine (214), a schedule based on the one or more determined sentiments.

[0052]

[0046] At step 310, method 300 comprises the steps of enabling, by the system 106, interaction among the one or more users as per the dynamically configured schedule.

[0053]

[0047] In one example embodiment, at step 308 and 310, the method 300 comprises the steps of analyzing, by the system 106, via the machine learning engine 214 or an artificial intelligence (Al) technique, the one or more sentiments of a plurality of users of the one or more users. The method 300 comprises the steps of determining, by the system 106, one or more emotional triggers associated with the plurality of users during the interaction based on the one or more sentiments. The method 300 comprises the steps of generating, by the system 106, one or more activities to engage the plurality of users during the interaction based on the one or more emotional triggers.

[0054]

[0048] In one example embodiment, at step 308 and 310, the method 300 comprises the steps of recording, by the system 106, the one or more emotional triggers among the plurality of users during the one or more activities. The method 300 comprises the steps of receiving, by the system 106, feedback associated with the one or more activities from the plurality of users. The method 300 comprises the steps of varying, by the system 106, the one or more activities during the predefined schedule based on the recorded one or more emotional triggers and the received feedback. The method 300 comprises the steps of enabling, by the system 106, the interaction among the plurality of users during varied one or more activities for a predetermined period. The method 300 comprises the steps of receiving, by the system 106, on or more real-time inputs from the plurality of users during the one or more activities. In response to adetermination of one or more conflicts based on the one or more real-time inputs, the method 300 comprises the steps of facilitating, by the system 106, one or more discussions among the plurality of users to mediate the one or more conflicts generated during the one or more activities.

[0055]

[0049] FIG. 4 illustrates an example block diagram representing user types and functionalities of the proposed system, in accordance with an example embodiment. The system 106 may comprise members 404 that access the system 106 for interacting with various users through the activities. For example, the members 404 may connect with other members through the gym connect platform 402. Further, the gym connect platform 402 may comprise trainers for training the members 404. An administrator 408 may be appointed by the gym connect platform 402 for managing the various activities associated with the gym connect platform 402. In addition, a supplier 410 may supply the requirements required by the members 404 of the gym connect platform 402.

[0056]

[0050] FIG. 5 illustrates an example block diagram representing various modules implemented by the proposed system, in accordance with an example embodiment. In an example embodiment, the users may use user devices 502 (previously UEs 102) for accessing the system 106 through the mobile application 504. The system 106 may comprise a backend server 506 and a content management module 508 for managing and providing the activities to the users. The user management module 510 may be connected to the backend server 506 for categorizing the users for various activities via a training module 512, a dating module 514, a forum module 516, and a sessions module 518 respectively. For example, in an embodiment, the users choosing dating as the activity may be categorized through the dating module 514 and one or more sessions associated with dating may be provided by the dating module 514 for the predetermined period.

[0057]

[0051] FIGs. 6A-6B illustrates an example interfaces (600A, 600B) implemented by the proposed system 106, in accordance with an example embodiment. In an example embodiment, the system 106 may comprise an interface 602 that allows the user / member to login 604 into the interface 602. Theinterface 602 may be accessed by the users by using a sign in 606 option and entering an email 608 and a password 610. Further, the interface 602 may comprise a “Forgot Password” field 612 that allows the users to remember 614 their password by providing various options. In another example embodiment, the users may access a gym connect platform 616 through logging into the interface 602. The gym connect platform 616 may further comprise a training module 618, a dating module 620, a forum module 622, a sessions module 624 respectively, and a user management module 626 respectively for allowing the users / members to access the various activities provided the system 106.

[0058]

[0052] As will be appreciated by those skilled in the art, the techniques described in the various embodiments discussed above are not routine, or conventional, or well understood in the art. The techniques discussed above provide for innovative solutions to address the challenges associated with generating holistic responses based on structural and semantic queries. The disclosed techniques offer several advantages over the existing methods as listed in below paragraphs. Here are examples of ML and Al technique s / algorithms that can be applied to the described invention:

[0059]

[0053] For sentiment analysis: Natural Language Processing (NLP) models (e.g., BERT, RoBERT a), Support Vector Machines (SVM) for text classification, Long Short-Term Memory (LSTM) networks for sequence analysis.

[0060]

[0054] For emotion detection: convolutional neural networks (CNNs) for voice tone analysis, recurrent neural networks (RNNs) for time-series data, multimodal emotion recognition models combining text, voice, and behavioural data.

[0061]

[0055] Dynamic Scheduling and Adaptation: reinforcement learning (e.g., Q-Learning, Deep Q-Networks), evolutionary algorithms for optimization, and Bayesian optimization for parameter tuning.

[0062]

[0056] Activity Recommendation: collaborative filtering (Matrix Factorization), clustering algorithms (e.g., K-Means, DBSCAN), neural collaborative filtering for personalized activity suggestions.

[0057] Conflict Mediation: decision trees and random forests for rule-based decision-making, multi-agent reinforcement learning for interaction modelling, generative adversarial networks (GANs) for simulating resolution scenarios.

[0063] Real-Time Feedback Analysis: online learning algorithms (e.g., Passive-Aggressive Algorithms), gradient boosting machines (e.g., XGBoost, LightGBM), time-series forecasting models (e.g., ARIMA, Prophet).

[0064]

[0058] The present disclosure introduces a system and a method for sentiment analysis of users using machine learning. Several of the key advantages of this solution include data processing through machine learning where ML models can analyze vast amounts of text data in a fraction of the time it would take a human. This is particularly useful for social media monitoring, customer feedback, or large datasets. Further, machine learning can process data and provide real-time sentiment insights, which are vital for businesses to react promptly to public opinion, customer concerns, or market trends.

[0065]

[0059] To summarize, the invention relates to an integrated system 106 for sentiment analysis that leverages advanced technologies such as machine learning (ML), artificial intelligence (Al), to create a dynamic and adaptive platform for sentiment analysis based on social interactions and collaborative activities. The system ensures real-time sentiment analysis, fostering meaningful and inclusive interactions.

[0066]

[0060] Real-world working example: A smart gym platform employs the integrated system (106) for sentiment analysis-based interaction to optimize group workouts and foster social engagement among gym-goers. The system enhances the gym experience by tailoring activities and interactions to users' real-time emotional states and feedback, ensuring inclusivity and motivation for all participants. A smart gym platform utilizes the integrated system (106) to optimize group workouts and foster social engagement among gym-goers. The system analyzes real-time emotional states and behavioural feedback to create an inclusive and adaptive fitness environment. During group fitness sessions, wearable trackers collect data such as heart rate, activity levels, and body temperature, while smart monitors analyze voice tones and text inputs fromparticipants in fitness apps. Behavioural data, such as pace consistency and rep counts, is also captured. Using the processor (202) and the machine learning engine (214), the system determines sentiments like fatigue, motivation, or frustration. For instance, a drop-in intensity paired with a negative tone of voice indicates demotivation.

[0067]

[0061] Based on the analyzed data, the system dynamically adapts the workout plan to align with group sentiments. If participants show signs of fatigue, the system may replace a high-intensity activity with a cooldown stretch. Conversely, high energy levels prompt the system to schedule more vigorous activities, such as HIIT routines. Additionally, the system identifies emotional triggers, such as disengagement, and introduces engaging activities like teambased fitness challenges to maintain group motivation.

[0068]

[0062] Participants provide feedback through the gym’s app, using emojis, quick polls, or voice inputs. In cases of conflicting preferences for workout difficulty, the system facilitates mediation by suggesting compromises, such as splitting the group into subgroups or proposing alternative activities. The system also records emotional responses during activities and continuously refines the workout based on participant engagement. For example, if engagement drops, the system may introduce gamified elements, such as a leader board competition, or vary music tracks to reinvigorate the group.

[0069]

[0063] Overall, the system handles the entire process, from receiving data and analyzing sentiments to dynamically reconfiguring activities and mediating conflicts. By tailoring the workout experience in real-time, the platform ensures an adaptive and collaborative fitness environment, allowing participants of varying fitness levels to stay engaged, motivated, and connected throughout the session.

Claims

CLAIMS:

1. An integrated system (106) for sentiment analysis-based interaction, the system (106) comprising:a processor (202);a memory (204) operatively coupled with the processor (202), wherein said memory (204) stores instructions which, when executed by the processor (202), cause the processor (202) to:receive data associated with one or more users, wherein the data comprises one or more parameters associated with a live interaction among the one or more users;analyze the one or more parameters of the live interaction to determine one or more sentiments associated with the one or more users involved in the live interaction;dynamically configure, via a machine learning engine (214), a schedule based on the one or more determined sentiments; andenable interaction among the one or more users as per the dynamically configured schedule.

2. The integrated system (106) according to claim 1, wherein the one or more parameters comprise at least one of a text-based interaction parameter associated with the one or more users, a voice-based interaction parameter associated with the one or more users, and one or more behavioural data associated with the one or more users during the live interaction.

3. The integrated system (106) according to claim 1, wherein the schedule is a predefined schedule, and to dynamically configure the predefined schedule, the processor (202) is configured to:analyze, by the machine learning engine (214) or an artificial intelligence (Al) technique, the one or more sentiments of a plurality of users of the one or more users;determine, one or more emotional triggers associated with the plurality of users during the interaction based on the one or more sentiments; andgenerate, one or more activities to engage the plurality of users during the interaction based on the one or more emotional triggers.

4. The integrated system (106) according to claim 3, wherein to enable interaction among the one or more users, the processor (202) is configured to:record, the one or more emotional triggers among the plurality of users during the one or more activities;receive feedback associated with the one or more activities from the plurality of users;vary the one or more activities during the predefined schedule based on the recorded one or more emotional triggers and the received feedback; andenable the interaction among the plurality of users during varied one or more activities for a predetermined period.

5. The integrated system (106) according to claim 4, wherein to receive feedback, the processor (202) is configured to:receive, on or more real-time inputs from the plurality of users during the one or more activities;in response to a determination of one or more conflicts based on the one or more real-time inputs; andfacilitate one or more discussions among the plurality of users to mediate the one or more conflicts generated during the one or more activities.

6. A method (300) for sentiment analysis-based interaction, the method (300) comprising:receiving (302), by a processor (202) associated with a system, data associated with one or more users, wherein the data comprises one or more parameters associated with a live interaction among the one or more users;analyzing (304), by the processor (202), the one or more parameters of the live interaction to determine one or more sentiments associated with the one or more users involved in the live interaction;dynamically configuring (306), by the processor (202), via a machine learning engine (214), a schedule based on the one or more determined sentiments; andenabling (308), by the processor (202), interaction among the one or more users as per the dynamically configured schedule.

7. The method (300) according to claim 6, wherein the one or more parameters comprise at least one of a text-based interaction parameter associated with the one or more users, a voice-based interaction parameter associated with the one or more users, and one or more behavioural data associated with the one or more users during the one or more interactions.

8. The method (300) according to claim 6, wherein the schedule is a predefined schedule, and for dynamically configuring the predefined schedule, the method comprises:analyzing, by the processor (202), via the machine learning engine (214) or an artificial intelligence (Al) technique, the one or more sentiments of a plurality of users of the one or more users;determining, by the processor (202), one or more emotional triggers associated with the plurality of users during the interaction based on the one or more sentiments; andgenerating, by the processor (202), one or more activities to engage the plurality of users during the interaction based on the one or more emotional triggers.

9. The method (300) according to claim 8, wherein for enabling interaction among the one or more users, the method comprises:recording, by the processor (202), the one or more emotional triggers among the plurality of users during the one or more activities;receiving, by the processor (202), feedback associated with the one or more activities from the plurality of users;varying, by the processor (202), the one or more activities during the predefined schedule based on the recorded one or more emotional triggers and the received feedback; andenabling, by the processor (202), the interaction among the plurality of users during varied one or more activities for a predetermined period.

10. The method (300) according to claim 9, wherein for receiving feedback, the method comprises:receiving, by the processor (202), one or more real-time inputs from the plurality of users during the one or more activities;in response to a determination of one or more conflicts based on the one or more real-time inputs;facilitating, by the processor (202), one or more discussions among the plurality of users to mediate the one or more conflicts generated during the one or more activities.

Images