Abstract
In our previous study, we used Naive Bayes to discriminate and quantify approval desire in tweets based on words. To correctly understand a sentence, it is important to consider not only words but also word relationships and grammar. In this study, we investigate the possibility of improving the accuracy of discrimination and quantification of the desire of approval in tweets by weighting word using dependency analysis results and examine and clarify the factors that may lead to improvement. The results of the experiment showed that the correlation coefficients between the classification results with weighting and the evaluators’ ratings increased compared to the correlation coefficients between the classification results without weighting and the evaluators’ ratings.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Murata, E., Tago, K., Jin, Q.: Linguistic and contextual analysis of SNS posts for approval desire, social computing and social media: design, user experience and impact. 14th International Conference (SCSM 2022), 24th HCI International Conference (HCII 2022), Proceedings, Part I, Lecture Notes in Computer Science (Springer), 13315, pp. 332–344 (2022)
Kim, Y.C., Shin, E., Cho, A., Jung, E., Shon, K., Shim, H.: SNS dependency and community engagement in urban neighborhoods: the moderating role of integrated connectedness to a community storytelling network. Commun. Res. 46(1), 7–32 (2019)
Marouf, A.A., Hasan, M., Mahmud, H.: Comparative analysis of feature selection algorithms for computational personality prediction from social media. IEEE Transactions on Computational Social Systems 7(3), 587–599 (2020)
Swartz, M., Crooks, A., Kennedy, W.G.: Diversity from emojis and keywords in social media. Proc. SMSociety’20: International Conference Proceeding Series, ACM, pp. 92–100 (2020)
Yoshida, S., Kitazono, J., Ozawa, S., Sugawara, T., Haga, T., Nakamura, S.: Sentiment analysis for various SNS media using Naïve Bayes classifier and its application to flaming detection. Proceedings 2014 IEEE Symposium on Computational Intelligence in Big Data, pp. 1–6 (2014)
Yamaoka, H., Sano, M.: Persona estimation using SNS based on naive bayes method. Proceedings the 32nd Annual Conference of the Japanese Society for Artificial Intelligence, JSAI2018 (2018). https://doi.org/10.11517/pjsai.JSAI2018.0_4Pin120 (In Japanese)
Koo, T., Carreras, X., Collins, M.: Simple semi-supervised dependency parsing. 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference, pp. 595–603 (2008)
Tago, K., Takagi, K., Kasuya, S., Jin, Q.: Analyzing influence of emotional tweets on user relationships using Naive Bayes and dependency parsing. World Wide Web 22(3), 1263–1278 (2019)
Miwa, M., Tatsuma, A., Aono, M.: Sentiment analysis of tweets focusing on the position of polarity words and on the emphasized and de-emphasized expressions. Forum on Information Technology 2, 227–228 (2014). (In Japanese)
Yahoo Ditransitive Analysis. https://developer.yahoo.co.jp/webapi/jlp/da/v2/parse.html. Accessed 19 June 2023
Japanese Thesaurus Associated Thesaurus. https://renso-ruigo.com. Accessed 19 June 2023
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Murata, E., Tago, K., Jin, Q. (2023). Investigating the Factors to Improve Discrimination of the Desire for Approval in Tweets by Incorporating Dependency Analysis. In: Mori, H., Asahi, Y., Coman, A., Vasilache, S., Rauterberg, M. (eds) HCI International 2023 – Late Breaking Papers. HCII 2023. Lecture Notes in Computer Science, vol 14056. Springer, Cham. https://doi.org/10.1007/978-3-031-48044-7_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-48044-7_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48043-0
Online ISBN: 978-3-031-48044-7
eBook Packages: Computer ScienceComputer Science (R0)