Network ideological and political education personalized guiding method based on emotional tendency recognition

Abstract

The invention provides a network ideological and political education personalized guiding method based on emotional tendency recognition, and aims to perform emotional analysis on network speech of college students through a natural language processing technology so as to recognize emotional tendencies of the college students. According to the method, speaking data of students in social media, forums and comment areas are collected in real time through web crawlers, and then emotional polarity judgment and emotional tendency recognition are conducted through a deep learning model such as LSTM. According to an analysis result, a personalized ideological and political education scheme is formulated in combination with personal backgrounds and requirements of students, and personalized customization of education contents and methods is realized through steps of emotional civilization cultivation, special group attention, education innovation in a new media environment, theory and practice combination and the like. The application of the method can improve the pertinence and effectiveness of ideological and political education, promote the cultivation of emotional civilization of students, and help cultivate new-age college students with positive emotional attitudes and correct values.

Description

Technical Field

[0001] The present invention relates to the field of educational technology, and in particular to a personalized guidance method for online ideological and political education based on emotion tendency recognition. Background Art

[0002] With the rapid development and popularization of Internet technology, cyberspace has become an important place for college students to socialize, study and entertain. In such an environment of information explosion and diverse viewpoints, college students' thoughts and emotional expressions are unprecedentedly active and complex. As a direct reflection of college students' emotions and attitudes, online speech contains rich emotional information and value orientations. The analysis and guidance of this information is particularly important.

[0003] Traditional ideological and political education methods often focus on face-to-face classroom teaching, lacking in-depth understanding and timely response to students' online behavior and emotional expression. This has led to limited guidance effects of ideological and political education in the online environment, making it difficult to meet students' personalized and diverse needs. In addition, the massive and instantaneous nature of online speech has also posed new challenges to ideological and political education workers. How to accurately capture students' emotional tendencies from a large amount of online data and formulate effective education strategies based on this has become an urgent problem to be solved.

[0004] In order to meet these challenges, it is necessary to apply modern information technology, especially natural language processing and big data analysis technology, to the field of online ideological and political education. Through these technologies, students' emotions and attitudes in cyberspace can be analyzed and understood more accurately, thus providing more precise and personalized guidance for ideological and political education. This can not only improve the interactivity and attractiveness of ideological and political education, but also help students form correct values ​​and world views and promote their all-round development. Summary of the invention

[0005] The present invention provides a personalized guidance method for online ideological and political education based on sentiment tendency recognition, which aims to realize sentiment analysis of students' online speech through natural language processing technology and big data analysis, and formulate personalized education guidance strategies accordingly. The method specifically includes the following steps:

[0006] The data collection step aims to comprehensively capture the behavior and emotional state of students in cyberspace and provide original materials for online ideological and political education. First, the source of data collection is determined by carefully selecting social media platforms, forums and comment areas where students are active. These platforms are the main places for students to communicate and express their opinions on a daily basis, and therefore are key channels for obtaining students' emotional expressions. Next, the crawling strategy of the web crawler is designed. This strategy includes defining the keywords to be crawled, setting a reasonable crawling frequency, and determining the specific scope of data crawling. The setting of keywords is based on the common language and hot topics of the student group to ensure that the collected data is representative and relevant. At the same time, the setting of the crawling frequency is intended to balance the real-time nature of the data and the load capacity of the server. Developing a web crawler is the core task of this step. The development of the crawler uses programming languages ​​such as Python, and uses libraries such as Scrapy and BeautifulSoup to build a crawler framework. The crawler needs to be able to intelligently simulate user behavior and identify and crawl data in various forms such as text, pictures, and videos. In addition, the crawler must also have a certain anti-crawler capability to ensure the continuity and stability of data collection. The collected raw data usually contains a lot of noise and irrelevant information, so data preprocessing becomes an indispensable link. The preprocessing step involves removing HTML tags, formatting data, filling missing values, etc. to improve the quality of the data. In addition, in order to ensure the security and privacy of the data, the information involving personal privacy is desensitized. Data storage is to save the preprocessed data in the database for subsequent analysis and processing. The design of the database takes into account the query efficiency and security of the data, and adopts database systems such as MySQL and MongoDB. Each data record is marked with a timestamp to reflect the data collection time, and the data is backed up regularly to prevent data loss. In order to improve the accuracy of sentiment analysis, some of the collected data are manually annotated. The annotation work is completed by a professional data annotation team, who annotate the data with sentiment polarity and emotion category according to the predefined sentiment label system. These annotated data will be used to train and optimize the sentiment analysis model and improve the recognition ability of the model. Finally, in order to maintain the timeliness of the data, the web crawler will run regularly to update the database in real time. Through this dynamic update mechanism, it is ensured that the data collection step can continuously provide the latest student emotion and behavior data for online ideological and political education.

[0007] In the sentiment analysis step, we first preprocess the collected text data to ensure the cleanliness and consistency of the data. This step includes removing irrelevant characters, punctuation marks, links, and word segmentation to convert the text into structured data. Preprocessing is the basis of sentiment analysis, which directly affects the accuracy of subsequent analysis. Next, we extract key features for sentiment analysis from the text through feature extraction technology. This usually involves building a bag-of-words model, converting the text into a vector form, and applying technologies such as TF-IDF to determine the weight of the vocabulary. Feature extraction is the core link of sentiment analysis, which determines the richness of the emotional information that the model can capture. Based on feature extraction, we use machine learning models such as support vector machines (SVM), convolutional neural networks (CNN), and recurrent neural networks (RNN) to train the featurized text data. During the model training process, we will adjust parameter settings, the number of training rounds, and the learning rate to optimize the performance of the model. This step is the key to achieving sentiment analysis, which involves the selection of models and the determination of training strategies. Subsequently, we use the trained model to judge the sentiment polarity of the text data. The model will assign a sentiment score to each text based on the feature vector and the learned weights to determine its sentiment tendency. This step is the key output of sentiment analysis, which directly affects the results of sentiment analysis. Furthermore, based on the judgment of sentiment polarity, we identify the specific types of emotions contained in the text, such as joy, anger, sadness, etc. This step can be achieved through deep learning technology, which can provide more detailed sentiment analysis results. Finally, we evaluate and optimize the sentiment analysis model. Indicators such as accuracy, recall rate and F1 score are used to measure the performance of the model, and the model is adjusted according to the evaluation results. This step ensures the accuracy and efficiency of sentiment analysis and provides a scientific basis for formulating personalized ideological and political education guidance strategies. Through this series of steps, the present invention can accurately identify students' emotional tendencies from a large number of online speeches.

[0008] In the step of developing personalized guidance strategies, we first use the results of sentiment analysis to conduct in-depth needs analysis in combination with students' personal backgrounds, interests and needs. This step involves collecting students' basic information, such as grade, major, hobbies, etc., as well as their behavioral data on online platforms, such as speaking frequency, interaction patterns, topics of interest, etc. Through these data, we can outline students' online behavioral characteristics and potential needs. Next, we analyze students' behavioral data and psychological data to determine their educational needs. Behavioral data includes students' online active time, types and frequency of participating topics, while psychological data may involve students' emotional state, stress level, etc., which can be inferred from sentiment analysis results. For example, if students are often active at night and their speeches tend to be negative, we may infer that students may face academic pressure or emotional problems. We optimize the content and form of ideological and political education programs based on the analysis results. This includes adjusting the relevance of educational topics to better attract students' attention and designing interactive links to increase students' participation. For example, for students interested in art, we can incorporate art elements into ideological and political education or invite experts in the field of art to give lectures. We develop personalized ideological and political education programs. This involves creating customized teaching materials, such as personalized reading materials, video content, and discussion topics, as well as arranging personalized tutoring and interactive activities. For example, for students who show a strong sense of social responsibility, we can provide volunteer service opportunities or organize relevant social practice activities. Through this series of steps, the present invention can ensure that the ideological and political education program matches the personality and needs of the students, thereby improving the pertinence and effectiveness of education. This personalized approach helps to enhance students' learning motivation and promote their all-round development.

[0009] In the step of formulating the personalized guidance strategy, first, based on the results of sentiment analysis, we conduct an in-depth needs analysis based on the students' personal background, including information such as their major field and grade, as well as their interests and needs. We determine their behavior patterns and potential concerns by analyzing the content, frequency and time of students' speeches on social media, as well as the types of online activities they participate in. For example, if students are most active between 22:00 and 23:59 in the evening, and their speeches tend to be academic topics, we use this data as evidence that they may be interested in evening academic discussion activities. Next, we analyze students' behavioral and psychological data to determine their educational needs. We evaluate students' emotional states through the output of the sentiment analysis model, such as positive sentiment scores above 6 points (out of 10 points) and negative sentiment scores below 3 points, and determine that they may be interested in environmental protection projects based on their participation in specific topics, such as more than 10 discussions on environmental protection topics. We optimize the content and form of ideological and political education programs based on these analysis results. We adjust the relevance of educational topics, such as adding case analysis related to students' majors, and design interactive sessions, such as online Q&A, to increase student participation. For example, for students majoring in engineering, we will add discussions on engineering ethics to the ideological and political courses and arrange online exchanges with engineers. Finally, we develop personalized ideological and political education programs, including creating customized teaching materials, such as recommending 5 reading materials related to each student's interests, and arranging personalized tutoring and interactive activities. For example, for students who show a strong sense of social responsibility, we will provide 3 different volunteer service opportunities and organize at least 2 related social practice activities. Through this series of refined steps and parameter settings, the present invention can ensure that the ideological and political education program matches the personality and needs of the students, thereby improving the pertinence and effectiveness of education, and helping students gain a more personalized and meaningful learning experience in ideological and political education.

[0010] In the special group attention step, we first build a detailed personal profile for each special group student. These profiles include not only basic information about the student, such as name, gender, age, etc., but also family background, academic performance, psychological assessment results, and special needs. For example, for a student with learning disabilities, the profile will record his learning style, type of disability, and past assessment reports in detail. Next, we update these profiles by continuously monitoring students' online behavior and psychological conditions. This includes analyzing the time students are active on social media, the emotional tendencies of their posts, and their engagement. For example, if a student's online comments frequently show negative emotions, such as anxiety or depression, this information will be recorded and used for further analysis. Using advanced data analysis techniques, such as cluster analysis or classification algorithms, we are able to identify groups of students with specific psychological characteristics from a large amount of data. This step is crucial to discovering students who may need additional support. For example, through analysis, we may identify a group of students who may face similar challenges in learning, such as test anxiety. For each identified special group, we design and implement specialized educational intervention plans. These plans are designed to meet the individual needs of students and help them overcome obstacles. For example, for students with social disorders, we may arrange social skills training and emotional education courses. In addition, we also provide one-on-one personalized psychological counseling for students in need. These counseling services are designed to help students deal with personal problems and enhance their emotional management ability and self-efficacy. Counseling content may include cognitive behavioral therapy, emotional support, and stress management. In order to ensure the effectiveness of the educational intervention plan, we regularly evaluate and adjust it based on students' feedback and progress. This includes monitoring students' academic performance, participation, and improvement in mental health. Through this continuous evaluation and adjustment, we can ensure that the educational intervention plan is always consistent with students' needs. The special group attention step of the present invention provides comprehensive support for special group students through the establishment of personal files, recording of behavioral and psychological conditions, data analysis identification, education intervention plan design, personalized psychological counseling and academic support, and regular evaluation and adjustment. These measures help students overcome personal challenges and achieve their academic and personal growth goals.

[0011] In the steps of educational innovation under the new media environment, we first focus on content production and produce ideological and political education content suitable for new media dissemination. For example, we will develop a series of short videos with a duration of no more than 3 minutes, each of which focuses on a specific ideological and political topic and presents it with an engaging story or case to ensure that the content is both refined and attractive. Next, we will use new media platforms to publish and promote ideological and political education content. Select appropriate new media platforms, such as Weibo, WeChat, Douyin, and Bilibili, which have become important channels for college students to obtain information due to their immediacy and interactivity. We will set up official accounts on these platforms to publish analytical videos, graphic interpretations, and interactive discussion content related to ideological and political education. In addition, we implement online interactive activities such as online Q&A and discussion boards to increase student participation. By setting up a weekly online Q&A session, students are encouraged to ask questions and participate in discussions. At the same time, an online discussion board function is developed to allow students to express their opinions and exchange ideas on specific topics, thereby increasing students' sense of participation and gain. We also use the data analysis function of new media platforms to gain a deep understanding of college students' interests and hobbies, so as to customize personalized ideological and political education content. Through accurate analysis of students' interests, learning habits and ideological trends, colleges and universities can personalize and accurately push educational content to improve the attractiveness and educational nature of the content. In order to improve teachers' information dissemination and interaction capabilities in the new media environment, we will organize training regularly to enable teachers to master new media tools and strategies. The training content includes the use of new media tools, content creative production, visual design, online communication and interactive skills, etc., to ensure that teachers can skillfully use new media tools for teaching. We attach importance to the design of ideological and political practice education, encourage students to participate in social practice activities such as volunteer service and community participation, closely integrate ideological and political education with real life, and enhance the practicality and effectiveness of education. Through these steps, the present invention can make full use of educational resources and tools in the new media environment, innovate the form and content of ideological and political education, improve the attractiveness and participation of education, and enable students to better understand and accept ideological and political education in interaction and experience.

[0012] In the step of combining theory with practice, we first set up a research team composed of education experts and scholars who are responsible for in-depth research on ideological and political education theory. This team meets regularly to discuss the latest research results and theoretical developments to ensure that our education methods can keep up with the times. In order to evaluate the effectiveness of practice, we have implemented a systematic evaluation mechanism. Through regular questionnaires, interviews and observations, we collect feedback from students and educators on the current education methods. This valuable data is used to evaluate the effectiveness of education methods and provide us with directions for future improvements. Based on these evaluation results, we have developed a standardized process for adjusting education methods. This includes continuous review and updating of teaching content, teaching methods and teaching resources. Our aim is to ensure that these elements can meet the needs of students and adapt to changes in society. In order to promote the combination of theory and practice, we regularly organize ideological and political education seminars. These seminars invite education experts, scholars, teachers and students to participate, providing a platform for all stakeholders to share their experiences and views. At these seminars, we jointly explore how to further improve ideological and political education. We have established a multi-channel feedback mechanism. This includes online surveys, emails and social media platforms to encourage students and educators to provide opinions and suggestions. These feedbacks are collected and analyzed regularly to guide the optimization of our educational methods. Finally, we implemented a series of improvement measures based on the results of theoretical research and feedback mechanisms. This may include updating the syllabus, introducing new teaching techniques and methods, increasing interaction and discussion sessions, and providing more personalized learning support. Through these measures, we ensure the close integration of ideological and political education theory and practice, and improve the quality and effectiveness of ideological and political education through continuous evaluation and improvement.

[0013] The method of the present invention can effectively improve the pertinence and effectiveness of online ideological and political education, help students form correct values ​​and world views, and promote their all-round development.

[0014] The above technical solution can bring the following technical effects:

[0015] 1. Improve the personalization and pertinence of ideological and political education: Through natural language processing technology, sentiment analysis of online speech can accurately identify students' emotional tendencies and values. This analysis provides accurate data support for ideological and political education, so that educational content and methods can be personalized according to the specific needs of each student, thereby improving the pertinence and effectiveness of education.

[0016] 2. Enhance students' emotional civilization and value education: The cultivation of emotional civilization is an important part of ideological and political education. Through emotional education, students can obtain healthy emotional support and rich emotional experience in emotional experience, and improve the level of emotional civilization. This helps students establish healthy self-cognition and good communication skills, and also promotes the development of students in the internalization of moral values ​​and personality cultivation.

[0017] 3. Achieve innovation in educational content and methods: Using big data analysis and new media technology, we can innovate the content and form of ideological and political education. By analyzing students' behavioral data and learning habits, educators can design more attractive and interactive educational content. At the same time, the use of new media platforms also provides ideological and political education with a wider range of dissemination channels and more diverse interactive methods, enhancing the appeal and influence of education. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 Flow chart of the personalized guidance method of the present invention

[0019] Figure 2 This is a flow chart of the new media educational content publishing process of the present invention

[0020] Figure 3 The data analysis flow chart of the present invention is DETAILED DESCRIPTION

[0021] The following will be combined with the attached embodiment of the present invention Figures 1 to 3 , the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] The present invention provides a personalized guidance method for online ideological and political education based on sentiment tendency recognition, which aims to realize sentiment analysis of students' online speech through natural language processing technology and big data analysis, and formulate personalized education guidance strategies accordingly. The method specifically includes the following steps:

[0023] In the data collection step, we first identified five major social media platforms including Weibo, WeChat, and Zhihu as data sources, which have more than 100 million daily active student users. We designed a web crawler and configured a crawling frequency of every 15 minutes to ensure the real-time nature of the data. At the same time, the crawling depth was set to 3 pages to balance the breadth of the data and the server load. The crawler was developed in Python, using the Scrapy framework and integrating text, image, and video crawling plug-ins. Data preprocessing included using regular expressions to remove HTML tags, data cleaning through the Pandas library, filling in missing values, and using the SHA-256 algorithm to desensitize personal privacy information. The collected data is stored in a cloud database, each data record is marked with a timestamp accurate to milliseconds, and the database read and write speed reaches 1,000 queries per second. In addition, we organized a data annotation team of 10 professionals to manually annotate 1% of the collected data for sentiment in order to train and optimize the sentiment analysis model. These annotated data cover three sentiment polarities: positive, negative, and neutral, as well as eight emotion categories: joy, anger, and sadness. The web crawler is set to automatically update the database every 24 hours to keep the data up to date. Through these precise parameter settings and strict data collection processes, we are able to efficiently collect and process students' behavior and emotional state data in cyberspace, providing accurate and comprehensive data support for subsequent sentiment analysis and personalized guidance strategy formulation.

[0024] In the sentiment analysis step, the collected text data is first preprocessed, including removing irrelevant characters, punctuation marks, links, etc., and performing word segmentation to convert the text into structured data. Then, key features are extracted through feature extraction techniques such as the bag-of-words model and the TF-IDF algorithm, where the parameters of the TF-IDF algorithm include setting the maximum number of features to 5000 to retain the most important words. Subsequently, the support vector machine (SVM) model is used for sentiment analysis, where the regularization parameter C of the SVM is set to 1.0, the kernel function selects RBF, and its γ parameter is set to 0.1 for model training. During the training process, the cross-validation method is used to divide the data set into 5 parts, each of which is used as a test set in turn, and the rest is used as a training set to evaluate the stability and accuracy of the model. After the model training is completed, a sentiment score is assigned to each text, and the score threshold is set to 0. A positive score represents positive sentiment, and a negative score represents negative sentiment. Furthermore, deep learning techniques, such as LSTM networks, are used to identify specific emotion types in texts, where the number of hidden layer units of the LSTM network is set to 128 and the learning rate is set to 0.001. Finally, the model is evaluated using indicators such as accuracy, recall, and F1 score, with the accuracy target set to above 90%, the recall target set to above 85%, and the F1 score target set to above 0.85 to ensure the high performance of the model. Through this series of refined steps and parameter settings, the present invention can accurately identify students' emotional tendencies from a large number of online speeches, providing a scientific basis for formulating personalized ideological and political education guidance strategies.

[0025] In the step of developing personalized guidance strategies, we first conduct an in-depth needs analysis based on the results of sentiment analysis, combined with students' personal backgrounds, including information such as their majors and grades, as well as their interests and needs. We determine their behavior patterns and potential concerns by analyzing the content, frequency, and time of students' speeches on social media, as well as the types of online activities they participate in. For example, if students are most active between 22:00 and 23:59 in the evening, and their speeches tend to be academic topics, we use this data as evidence that they may be interested in evening academic discussion activities. Next, we analyze students' behavioral and psychological data to determine their educational needs. We evaluate students' emotional states through the output of sentiment analysis models, such as positive sentiment scores above 6 points (out of 10 points) and negative sentiment scores below 3 points, and determine that they may be interested in environmental protection projects based on their participation in specific topics, such as more than 10 discussions on environmental protection topics. We optimize the content and form of ideological and political education programs based on these analysis results. We adjust the relevance of educational topics, such as adding case analysis related to students' majors, and design interactive sessions, such as online Q&A, to increase student participation. For example, for students majoring in engineering, we will add discussions on engineering ethics to the ideological and political courses and arrange online exchanges with engineers. We develop personalized ideological and political education programs, including creating customized teaching materials, such as recommending 5 reading materials related to each student's interests, and arranging personalized tutoring and interactive activities. For example, for students who show a strong sense of social responsibility, we will provide 3 different volunteer service opportunities and organize at least 2 related social practice activities. Through this series of refined steps and parameter settings, the present invention can ensure that the ideological and political education program matches the personality and needs of the students, thereby improving the pertinence and effectiveness of education, and helping students gain a more personalized and meaningful learning experience in ideological and political education.

[0026] In the emotional civilization cultivation step of the present invention, we carefully designed and implemented a series of emotional education courses, including key topics such as self-cognition, empathy cultivation, and social skills improvement, to ensure that there is at least one 45-minute course per week to strengthen students' emotional cognition and expression ability. In addition, we organize at least one emotional education workshop per month to promote the improvement of students' emotional understanding ability through 15-minute interactive sessions such as role-playing and scenario simulation. At the same time, we use evaluation tools such as self-assessment questionnaires and teacher evaluation scales to conduct at least one evaluation per semester to ensure the effectiveness of educational activities. The implementation of these measures not only improves students' emotional civilization, but also promotes their better communication and interaction skills in social life, helps them form a healthy self-awareness and positive values, and provides a comprehensive and systematic emotional education experience for cultivating individuals with high emotional literacy.

[0027] In the special group attention step, we first create a personal profile for each special group student, recording in detail information including the student's name, gender, age, home address, contact information, and academic performance. At the same time, we collect the student's active time period on social media (such as 20:00 to 22:00 in the evening), the emotional tendency of the posting (positive emotional score greater than 6 points, negative emotional score less than 4 points), and participation indicators (such as posting at least 5 times a week). Using data analysis technology, we conduct quantitative analysis of students' behavior and psychological conditions, and identify student groups that may need additional support by setting thresholds, such as social activity lower than 30% of the class average. For these students, we design personalized educational intervention plans, including one-on-one psychological counseling at least once a week, each counseling lasting 50 minutes, and customized academic support plans, such as providing additional after-school tutoring time, each time not less than 1 hour. In addition, we conduct an effectiveness evaluation every three months. We evaluate the effectiveness of the intervention plan through psychological assessment tools (such as the Mental Health Scale, with a scoring scale of 0 to 100 points) and tracking and analysis of academic performance. We adjust the tutoring frequency and teaching content based on the evaluation results to ensure that every student receives appropriate support and resources to promote their all-round development.

[0028] In the steps of educational innovation under the new media environment, we carefully produced a series of short videos and animations with a duration of no more than 3 minutes, focusing on new media communication, publishing content at least once a week, covering multiple aspects of ideological and political education, and promoting it through platforms such as Weibo, WeChat, Douyin, and Bilibili; at the same time, we implemented online Q&A and discussion board interactive activities once a week, each lasting 1 hour, to enhance student participation and interactivity; using the data analysis function of the platform, we have a deep understanding of student interests and push personalized content at least once a month, such as pushing in-depth articles and videos to followers of environmental protection topics; in addition, we regularly organize teacher training, including the use of new media tools, content creative production, visual design, and online interactive skills, at least once a quarter, to enhance teachers' new media teaching ability; we also encourage students to participate in social practice activities, such as organizing volunteer services at least once a month, closely integrating ideological and political education with real life, thereby improving the practicality and effectiveness of education. Through these innovative measures, the present invention aims to enhance the attractiveness and participation of ideological and political education, so that students can better understand and accept ideological and political education in interaction and experience.

[0029] In the step of combining theory with practice, we formed a research team of 10 education experts and scholars to conduct in-depth research and update the theory of ideological and political education, and held seminars at least twice a month to discuss the latest research results. In order to evaluate the effectiveness of practice, we implemented an evaluation mechanism to collect feedback from at least 500 students and 100 educators through monthly questionnaires, quarterly in-depth interviews and continuous classroom observations to ensure that the sample is representative. Based on these data, we conduct standardized review and update of educational methods at least once a semester to adapt to social changes and student needs. In addition, we organize a large-scale ideological and political education seminar every six months, inviting at least 20 field experts and 50 students to participate and jointly discuss the improvement of educational methods. We also established a feedback mechanism to collect at least 1,000 opinions and suggestions per month through an online survey platform. Through these feedbacks, we implement improvement measures for educational content and methods at least twice a year, including updating the syllabus, introducing new teaching technologies, increasing interactive links and providing personalized learning support, to ensure that the quality and effectiveness of ideological and political education are continuously improved.

[0030] The method of the present invention can effectively improve the pertinence and effectiveness of online ideological and political education, help students form correct values ​​and world views, and promote their all-round development.

[0031] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A personalized guidance method for online ideological and political education based on emotional tendency recognition, characterized in that: The following steps are involved: s1. Data collection step: using web crawler technology to collect students’ speech data in social media, forums, and comment areas in real time; s2. Sentiment analysis step: using natural language processing technology to perform semantic analysis on the collected data, extract sentiment keywords, determine the sentiment polarity of the text based on the sentiment dictionary and machine learning model, and identify the specific sentiment type contained in the text; s3. Steps for formulating personalized guidance strategies: Based on the results of sentiment analysis, combined with students’ personal backgrounds, interests and needs, conduct demand analysis, analyze students’ behavioral and psychological data, determine students’ educational needs, optimize the content and form of ideological and political education programs, and formulate personalized ideological and political education programs; s4. Steps for cultivating emotional civilization, including emotional value education and emotional ability cultivation, imparting emotion-related values ​​and morals, and training students' emotional cognition and emotional expression abilities; s5. Steps for paying attention to special groups: establish personal files for special groups, record their online behaviors and psychological conditions, and provide personalized psychological counseling and academic support; s6. Steps for educational innovation in the new media environment: producing ideological and political education content suitable for new media dissemination, and using new media platforms to publish and promote ideological and political education content; s7. Combine theory with practice, conduct in-depth research on ideological and political education theory, and adjust and optimize educational methods based on practical results.

2. A personalized guidance method for online ideological and political education based on emotional tendency recognition, characterized in that: The sentiment analysis step includes using the support vector machine (SVM) algorithm to perform preliminary classification of text data, using deep learning techniques such as convolutional neural networks (CNN) or recurrent neural networks (RNN) to fine-tune the preliminary classification results, and combining linguistic rules and sentiment dictionaries to manually correct boundary cases that the model cannot judge.

3. A personalized guidance method for online ideological and political education based on emotional tendency recognition, characterized in that: The steps of formulating personalized guidance strategies include using cluster analysis to group students, determining the educational needs of different groups, designing customized online courses and interactive modules based on the characteristics of student groups, and developing a recommendation system to recommend personalized learning resources based on students' historical interaction data.

4. A personalized guidance method for online ideological and political education based on emotional tendency recognition, characterized in that: The steps of cultivating emotional civilization include developing a series of emotional education courses covering self-cognition, empathy cultivation and social skills improvement, organizing emotional education workshops, improving students' emotional understanding ability through role-playing and situational simulation activities, implementing emotional education evaluation, and evaluating the effectiveness of emotional education through questionnaires and behavioral observations.

5. A personalized guidance method for online ideological and political education based on emotional tendency recognition, characterized in that: The special group attention step includes identifying student groups with specific psychological characteristics through data analysis, designing special educational intervention plans for each special group, providing one-on-one online psychological counseling services, and targeted academic guidance.

6. A personalized guidance method for online ideological and political education based on emotional tendency recognition, characterized in that: Among the steps of educational innovation in the new media environment are the development of ideological and political education applications suitable for mobile devices, the production of short videos and animations to attract students' attention, and the implementation of online interactive activities such as online Q&A and discussion boards to increase student participation.

7. A personalized guidance method for online ideological and political education based on emotional tendency recognition, characterized in that: The steps of combining theory with practice include regularly organizing ideological and political education seminars, inviting education experts and students to participate, establishing a feedback mechanism to collect opinions and suggestions from students and educators, and regularly updating education content and teaching methods based on the feedback results.

Images