Abstract
Rapid growth of social network service (SNS) has drawn significant attention from the publics. Existing research indicated that emotional state and behavioral tendency of SNS users can be identified and predicted through sentiment analysis. However, it is found that not only the posts can express user’s emotions but the overall environmental conditions faced by the user may lead to the generation of different emotions based on the cognitive theory of emotion and observation. Therefore, it may lead to bias between the sentiment analysis results and the actual situation if only analyzing the post. This study targets to propose an extendable sentiment monitoring model which considers the actual environment of users in SNS. Through this model, the result of sentiment analysis is closer to reality. By analyzing the content of users’ continuous posts, the sentiment analysis can take into account the pre- and post-textual relationships. The classification result of external affecting sentiment factors by K-means is used as criteria for weighting method to adjust the results of sentiment analysis based on BERT. Finally, the time series analysis is used to predict sentiment tendency monitor sentiment changes. The experiment results show that the training and validation accuracy are 89.24% and 84.00%, respectively. By our weighting method to revise the BERT results, the F1 score is improved from 0.839 to 0.850.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Worldometers.info website: Real Time Statistics Project. Worldometers.info., Dover, Delaware, USA. http://www.internetlivestats.com/. Accessed 19 Jan 2022
Picard, R.W.: Affective Computing. MIT Press, Cambridge (1997)
Kishinani, K.: Emotion detection from text using PyTorch and federated learning. Opensource project on GitHub. https://github.com/karankishinani/Emotion-detection-from-text-using-PyTorch-and-Federated-Learning. Accessed 19 Jan 2022
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Yang, G., Baek, S., Lee, J.W., Lee, B.: Analyzing emotion words to predict severity of software bugs: a case study of opensource projects. In: Symposium on Applied Computing (SAC 2017), New York, USA, pp. 1280–1287 (2017)
Solomon, R.C.: On emotions as judgments. Am. Philos. Q. 183–191 (1988)
Wang, Y.J., Yen, N., Hung, J.C.: Design of a multi-dimensional model for UGC-based emotion analysis. In: 2019 International Conference on Computational Science and Computational Intelligence Proceedings, pp. 1383–1387. IEEE, USA (2019)
Plutchik, R.: The nature of emotions: human emotions have deep evolutionary roots, a fact that may explain their complexity and provide tools for clinical practice. Am. Sci. 89(4), 344–350 (2001)
Demszky, D., Movshovitz-Attias, D., Ko, J., Cowen A., Nemade, G., Ravi, S.: GoEmotions: a dataset of fine-grained emotions. In: The 58th Annual Meeting of the Association for Computational Linguistics Proceedings, pp. 4040–4054. Association for Computational Linguistics (2020)
Alsaeedi, A., Khan, M.Z.: A study on sentiment analysis techniques of Twitter data. Int. J. Adv. Comput. Sci. Appl. 10(2), 361–374 (2019)
Himelboim, I., Sweetser, K.D., Tinkham, S.F., Cameron, K., Danelo, M., West, K.: Valence-based homophily on Twitter: network analysis of emotions and political talk in the 2012 presidential election. New Media Soc. 18(7), 1382–1400 (2014)
Wang, W., Chen, L., Thirunarayan, K., Sheth, A.P.: Harnessing Twitter “Big Data” for automatic emotion identification. In: International Conference on Privacy, Security, Risk and Trust and 2012 International Conference on Social Computing Proceedings, Amsterdam, pp. 587–592 (2012)
Lee, Y.J., Huang, J.J., Wang, H.Y., Zhong, N.: Study of emotion recognition based on fusion multi-modal bio-signal with SAE and LSTM recurrent neural network. J. Commun. 38(12), 109–120 (2017)
Rout, J.K., Choo, K.-K., Dash, A.K., Bakshi, S., Jena, S.K., Williams, K.L.: A model for sentiment and emotion analysis of unstructured social media text. Electron. Commer. Res. 18(1), 181–199 (2017). https://doi.org/10.1007/s10660-017-9257-8
Seyeditabari, A., Tabari, N., Gholizadeh, S., Zadrozny, W.: Emotion detection in text: focusing on latent representation. arXiv preprint arXiv:1907.09369 (2019)
Kanclerz, K., Miłkowski, P., Kocoń, J.: Cross-lingual deep neural transfer learning in sentiment analysis. Procedia Comput. Sci. 176, 128–137 (2020)
Arpit, D., et al.: A closer look at memorization in deep networks. In: Proceeding of 34th International Conference on Machine Learning (ICML), vol. 70, pp. 233–242 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, Y., Yen, N., Jin, Q. (2022). An Extendable Sentiment Monitoring Model for SNS Considering Environmental Factors. In: Meiselwitz, G. (eds) Social Computing and Social Media: Design, User Experience and Impact. HCII 2022. Lecture Notes in Computer Science, vol 13315. Springer, Cham. https://doi.org/10.1007/978-3-031-05061-9_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-05061-9_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-05060-2
Online ISBN: 978-3-031-05061-9
eBook Packages: Computer ScienceComputer Science (R0)