Skip Abstract Section
Abstract
Emotion analysis on Sina Weibo has a great impetus for government agencies to survey public opinion and enterprises to track market demand. Most of the existing emotion analysis work on Sina Weibo focuses on mining the information contained in a single Weibo, ignoring the problem of inaccurate information extraction caused by the lack of contextual information in Weibo texts. Inspired by humans judging user emotional states from Weibo texts, this article creates a Weibo text five-category emotion classification dataset based on active users and proposes a user-based hierarchical network for Weibo emotion analysis. First, use the multi-head attention mechanism and convolutional neural network set in the information extraction module to analyze a single Weibo text to fully extract the emotional information contained in the text; at the same time, through the moving window set in the relevant information capture module, obtain other Weibo texts posted by the same user within a period, and capture the effective correlation information between Weibo texts; then, the dual text representation obtained above is concatenated, and through the information interaction layer, the relevant information is retrieved again, and the text representation is updated; finally, the classifier output the five-category emotion labels corresponding to each Weibo text. We demonstrate the model’s effectiveness through experiments and analysis in the results.
- [1] . 2018. Multi-layers convolutional neural network for twitter sentiment ordinal scale classification. In Proceedings of the International Conference on Soft Computing and Data Mining. Springer, 446–454.Google Scholar
Cross Ref
- [2] . 2016. Opinion mining and information fusion: A survey. Info. Fusion 27 (2016), 95–110.Google ScholarDigital Library
- [3] . 2012. The impact of polices on government social media usage: Issues, challenges, and recommendations. Govern. Info. Quart. 29, 1 (2012), 30–40.Google ScholarCross Ref
- [4] . 2010. A hierarchical classifier applied to multi-way sentiment detection. In Proceedings of the 23rd International Conference on Computational Linguistics (COLING’10). 62–70.Google ScholarDigital Library
- [5] . 2017. On the role of text preprocessing in neural network architectures: An evaluation study on text categorization and sentiment analysis. Retrieved from https://arXiv:1707.01780.Google Scholar
- [6] . 2019. Understanding emotions in text using deep learning and big data. Comput. Hum. Behav. 93 (2019), 309–317.Google ScholarDigital Library
- [7] . 2015. Visualizing market structure through online product reviews: Integrate topic modeling, TOPSIS, and multi-dimensional scaling approaches. Electr. Comm. Res. Appl. 14, 1 (2015), 58–74.Google ScholarDigital Library
- [8] . 2015. Convolutional neural network for sentence classification. Master’s Thesis. University of Waterloo.Google Scholar
- [9] . 2016. Very deep convolutional networks for natural language processing. Retrieved from https://arXiv:1606.01781.Google Scholar
- [10] . 2004. Emotions revealed. Bmj 328, Suppl S5 (2004).Google ScholarCross Ref
- [11] . 2009. Twitter sentiment analysis. Entropy 17 (2009), 252.Google Scholar
- [12] . 2018. Microblog users’ Big-Five personality prediction based on multi-task learning. J. Univ. Chinese Acad. Sci. 35, 4 (2018), 550.Google Scholar
- [13] . 2020. Sentiment classification using a single-layered BiLSTM model. IEEE Access 8 (2020), 73992–74001.Google ScholarCross Ref
- [14] . 2020. Chinese short text classification with mutual-attention convolutional neural networks. ACM Trans. Asian Low-Res. Lang. Info. Process. 19, 5 (2020), 1–13.Google ScholarDigital Library
- [15] . 2019. A deep learning-based approach for multi-label emotion classification in tweets. Appl. Sci. 9, 6 (2019), 1123.Google ScholarCross Ref
- [16] . 2018. weibo_senti_100k Dataset. https://github.com/SophonPlus/ChineseNlpCorpus/blob/master/datasets/weibo_senti_100k.Google Scholar
- [17] . 2015. Twitter-airline-sentiment Dataset. Retrieved from https://www.kaggle.com/crowdflower/twitter-airline-sentiment.Google Scholar
- [18] . 2014. A convolutional neural network for modelling sentences. Retrieved from https://arXiv:1404.2188.Google Scholar
- [19] . 2014. A convolutional neural network for modelling sentences. Retrieved from https://arXiv:1404.2188.Google Scholar
- [20] . 2017. ALGA: Adaptive lexicon learning using genetic algorithm for sentiment analysis of microblogs. Knowl.-based Syst. 122 (2017), 1–16.Google ScholarDigital Library
- [21] . 2016. eSAP: A decision support framework for enhanced sentiment analysis and polarity classification. Info. Sci. 367 (2016), 862–873.Google ScholarDigital Library
- [22] . 2017. How the news media activate public expression and influence national agendas. Science 358, 6364 (2017), 776–780.Google ScholarCross Ref
- [23] . 2009. Modeling fuzzy multi-period production planning and sourcing problem with credibility service levels. J. Comput. Appl. Math. 231, 1 (2009), 208–221.Google ScholarDigital Library
- [24] . 2016. Sentiment analysis for low resource languages: A study on informal Indonesian tweets. In Proceedings of the 12th Workshop on Asian Language Resources (ALR’12). 123–131.Google Scholar
- [25] . 2016. Mining perceptual maps from consumer reviews. Decis. Supp. Syst. 82 (2016), 12–25.Google ScholarDigital Library
- [26] . 2022. A novel deep learning-based sentiment analysis method enhanced with emojis in microblog social networks. Enterprise Info. Syst. (2022), 1–22.Google Scholar
- [27] . 2020. Sentiment analysis by fusing text and location features of geo-tagged tweets. IEEE Access 8 (2020), 181014–181027.Google ScholarCross Ref
- [28] . 2020. Hybrid neural network for Sina Weibo sentiment analysis. IEEE Trans. Comput. Soc. Syst. 7, 4 (2020), 983–990.Google ScholarCross Ref
- [29] . 2021. Improving sentiment analysis accuracy with emoji embedding. J. Safety Sci. Resil. 2, 4 (2021), 246–252.Google ScholarCross Ref
- [30] . 2017. A method for multi-class sentiment classification based on an improved one-vs-one (OVO) strategy and the support vector machine (SVM) algorithm. Info. Sci. 394 (2017), 38–52.Google ScholarDigital Library
- [31] . 2022. Let the big data speak: Collaborative model of topic extract and sentiment analysis COVID-19 based on weibo data. In Proceedings of the International Conference on Adaptive and Intelligent Systems. Springer, 264–275.Google ScholarDigital Library
- [32] . 2014. NLPCC2014 Dataset. Retrieved from http://tcci.ccf.org.cn/conference/2014/pages/page04_dg.html.Google Scholar
- [33] . 2015. Understanding LSTM networks. Olah C. Understanding LSTM Networks.Google Scholar
- [34] . 2020. Improving the performance of sentiment analysis of tweets containing fuzzy sentiment using the feature ensemble model. IEEE Access 8 (2020), 14630–14641.Google ScholarCross Ref
- [35] . 2019. Personality prediction of Microblog user based on behavior information. J. Beijing Info. Sci. Technol. Univ.3 (2019), 32–38.Google Scholar
- [36] . 2015. A survey on opinion mining and sentiment analysis: Tasks, approaches and applications. Knowl.-based Syst. 89 (2015), 14–46.Google ScholarDigital Library
- [37] . 2017. SemEval-2017 task 4: Sentiment analysis in Twitter. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval’17). 502–518.Google ScholarCross Ref
- [38] . 2015. Sentiment analysis: A review and comparative analysis of web services. Info. Sci. 311 (2015), 18–38.Google ScholarDigital Library
- [39] . 2009. Tweet the debates: Understanding community annotation of uncollected sources. In Proceedings of the 1st SIGMM Workshop on Social Media. 3–10.Google ScholarDigital Library
- [40] . 2011. Twitter polarity classification with label propagation over lexical links and the follower graph. In Proceedings of the 1st Workshop on Unsupervised Learning in Natural Language Processing (NLP’11). 53–63.Google Scholar
- [41] . 2018. Detecting users’ anomalous emotion using social media for business intelligence. J. Comput. Sci. 25 (2018), 193–200.Google ScholarCross Ref
- [42] . 2009. A survey on sentiment detection of reviews. Expert Syst. Appl. 36, 7 (2009), 10760–10773.Google ScholarDigital Library
- [43] . 2012. Sentiment strength detection for the social web. J. Amer. Soc. Info. Sci. Technol. 63, 1 (2012), 163–173.Google ScholarDigital Library
- [44] . 2010. Sentiment strength detection in short informal text. J. Amer. Soc. Info. Sci. Technol. 61, 12 (2010), 2544–2558.Google ScholarDigital Library
- [45] . 2021. Research on sentiment classification of micro-blog short text based on topic clustering. In Journal of Physics: Conference Series, Vol. 1827. IOP Publishing, 012160.Google ScholarCross Ref
- [46] . 2017. Attention is all you need. Adv. Neural Info. Process. Syst. 30 (2017).Google Scholar
- [47] . 2021. A sentiment classification method of web social media based on multidimensional and multilevel modeling. IEEE Trans. Industr. Info. 18, 2 (2021), 1240–1249.Google ScholarCross Ref
- [48] . 2021. SAEP: A surrounding-aware individual emotion prediction model combined with T-LSTM and memory attention mechanism. Appl. Sci. 11, 23 (2021), 11111.Google ScholarCross Ref
- [49] . 2006. Recognizing strong and weak opinion clauses. Comput. Intell. 22, 2 (2006), 73–99.Google ScholarCross Ref
- [50] . 2022. Joint intent detection model for task-oriented human-computer dialogue system using asynchronous training. Transactions on Asian and Low-Resource Language Information Processing. (2022).Google ScholarDigital Library
- [51] 2018. User emotion modeling and anomaly detection based on social media. J. Chinese Info. Process. 32, 4 (2018), 120–129.Google Scholar
- [52] . 2019. An improved algorithm for sentiment analysis based on maximum entropy. Soft Comput. 23, 2 (2019), 599–611.Google ScholarDigital Library
- [53] . 2016. Cached long short-term memory neural networks for document-level sentiment classification. Retrieved from https://arXiv:1610.04989.Google Scholar
- [54] . 2020. Micro-blog sentiment analysis based on emoticon preferences and emotion commonsense. In Proceedings of the International Conference on Applications and Techniques in Cyber Security and Intelligence. Springer, 838–844.Google Scholar
- [55] . 2020. Micro-blog sentiment classification method based on the personality and bagging algorithm. Future Internet 12, 4 (2020), 75.Google ScholarCross Ref
- [56] . 2018. Deep learning for sentiment analysis: A survey. Wiley Interdisc. Rev.: Data Min. Knowl. Discov. 8, 4 (2018), e1253.Google ScholarCross Ref
- [57] . 2012. Weakness finder: Find product weakness from Chinese reviews by using aspects-based sentiment analysis. Expert Syst. Appl. 39, 11 (2012), 10283–10291.Google ScholarDigital Library
- [58] . 2021. Weibo Annual Report. Retrieved from https://baijiahao.baidu.com/s?id=1726279068555424418&wfr=spider&for=pc.Google Scholar
Index Terms
- User-based Hierarchical Network of Sina Weibo Emotion Analysis
Recommendations
Automatic detection of rumor on Sina Weibo
MDS '12: Proceedings of the ACM SIGKDD Workshop on Mining Data SemanticsThe problem of gauging information credibility on social networks has received considerable attention in recent years. Most previous work has chosen Twitter, the world's largest micro-blogging platform, as the premise of research. In this work, we shift ...
Topical differences between Chinese language Twitter and Sina Weibo
WWW '16 Companion: Proceedings of the 25th International Conference Companion on World Wide WebSina Weibo, China's most popular microblogging platform, is considered to be a proxy of Chinese social life. In this study, we contrast the discussions occurring on Sina Weibo and on Chinese language Twitter in order to observe two different strands of ...
Content-based emotion classification in online social networks for Chinese Microblogs
ACSW '17: Proceedings of the Australasian Computer Science Week MulticonferenceRecent years, social networks are popular throughout the whole world. In China in particular, more people spend their time on social networks. Sina Weibo, as the most popular microblogs in China, records millions of microblogs from different population. ...
Comments