Abstract
Emotion analysis is a specialized aspect of sentiment analysis that involves assessing and comprehending the emotions conveyed within textual data. This analytical process, applied to users’ emotions, serves various practical purposes, including healthcare, public opinion analysis on diverse subjects, criminal detection, and personalized recommendations. In this work, two distinct approaches have been presented-a quantitative approach and a fuzzy approach-to extract meaningful rules that reveal associations between various emotion classes present in users’ posts on social media platforms. The proposed methodology is evaluated using a dataset of Twitter users, categorizing emotions according to Ekman’s six classes. Several experiments have been conducted, considering different minimum support and minimum confidence thresholds. Promising results are obtained, as both methods effectively identify associations among different emotion classes present in users’ tweets. Identifying such associations can provide valuable insights, such as how emotion words present from any emotion class determines the presence of emotion words from other emotion class in the tweets of a user. Such findings will definitely be useful for the psychologist to study the emotion psychology of people and in the study of personality of people.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Availability of data and materials
If required data can be provided.
Code availability
If required, code can be provided.
References
Agrawal R, Imieli’nski T, Swami A (1993) Mining association rules between sets of items in large databases. J Appl Manag Entrep 22(01):207–216
Agrawal R, Srikant R (2000) Fast algorithms for mining association rules. In: Proceedings of 20th international conference on very large data bases VLDB, vol 1215, no 08
Alhuzali H, Zhang T, Ananiadou S (2022) Emotions and topics expressed on twitter during the Covid-19 pandemic in the United Kingdom: comparative geolocation and text mining analysis. J Med Int Res 24(10):40323
Cardone B, Martino FD, Miraglia V (2023) A fuzzy-based emotion detection method to classify the relevance of pleasant/unpleasant emotions posted by users in reviews of service facilities. Appl Sci 13(10):5893
Delgado M, Marín N, Sánchez D, Vila MA (2003) Fuzzy association rules: general model and applications. IEEE Trans Fuzzy Syst 11(2):214–225
Diaz-Garcia JA, Ruiz AD, Martin-Bautista MJ (2019) Generalized association rules for sentiment analysis in Twitter. Flex Query Answ Syst 11529:166–175
Ekman P (1999) Basic emotions. In: Handbook of cognition and emotion, vol 98, no 16, pp 45–60
Estrada MB, ZatarainCabada R, Oramas R, Graff M (2020) Opinion mining and emotion recognition applied to learning environments. Expert Syst Appl 150(02):113265
Gaind B, Syal V, Padgalwar S (2019) Emotion detection and analysis on social media. arXiv:1901.08458v2
Gavriel Meirovich G, Bahnan N, Haran E (2013) The impact of quality and emotions in customer satisfaction. J Appl Manag Entrep 18:27–50
Gligorić K, Anderson A, West R (2018) How constraints affect content: the case of Twitter’s switch from 140 to 280 characters. In: 12th international AAAI conference on web and social media, ICWSM, pp 596–599
Gyenesei A (2000) Determining fuzzy sets for quantitative attributes in data mining problems. Computer Science, Mathematics
Hakak N, Mohd M, Kirmani M, Mohd M (2017) Emotion analysis: a survey. In: International conference on computer, communications and electronics (Comptelix), pp 397–402
Kuok CM, Fu A, Wong MH (1998) Mining fuzzy association rules in databases. SIGMOD Rec 27(01):41–46
Li L, Bhardwaj A (2022) Emotion analysis method of teaching evaluation texts based on deep learning in big data environment. J Appl Manag Entrep 18(01):27–50
Mathew MK (2021) Emotion recognition systems and emotion correlation mining. Int J Eng Res Technol 09(07):24–28
Parrott W (2001) Emotions in social psychology, key readings in social psychology. Psychology Press, Philadelphia
Plutchik R (1980) A general psychoevolutionary theory of emotion. Theor Emot 1:3–33
Ranganathan J, Tzacheva A (2019) Emotion mining in social media data. Procedia Comput Sci 159:58–66
Safa R, Edalatpanah SA, Sorourkhah A (2023) Predicting mental health using social media: a roadmap for future development. In: Deep learning in personalized healthcare and decision support, pp 285–303
Sharma A, Ganpati A (2021) An enhanced approach for sentiment analysis using association rule mining. Int J Res Appl Sci Eng Technol (IJRASET) 9(12):913–918
Shi W, Xue G, Yin X, He S, Wang H (2022) DRMM: a novel data mining based emotion transfer detecting method for emotion prediction of social media. J Inf Sci 08(01):016555152211007
Srikant R, Agrawal R (1996) Mining quantitative association rules in large relational tables. In: ACM SIGMOD conference
Vohra A, Garg R (2023) Correction to: deep learning based sentiment analysis of public perception of working from home through tweets. J Intell Inf Syst 60(275):255–274
Zheng H, He J, Huang G, Zhang Y, Wang H (2019) Dynamic optimisation based fuzzy association rule mining method. Int J Mach Learn Cybern 10(08):2187–2198
Acknowledgements
N/A.
Funding
N/A.
Author information
Authors and Affiliations
Contributions
A collection of user tweets is preprocessed and using these preprocessed tweets a quantitative dataset has been created by using the emotional words present in the tweet. Here, the labels of Ekman’s six emotion classes have been considered for base emotion classes for analysis of the emotional words. As the traditional association rule mining algorithms cannot be directly applied on quantitative data, so, the quantitative dataset is converted into Boolean data and Fuzzy data. After the conversion, for each dataset a set of extended emotion classes is generated from Ekman’s six emotion classes. After that different association rules are mined for extended emotion class sets.
Corresponding author
Ethics declarations
Ethical approval
This research did not contain any studies involving animal or human participants, nor did it take place on any private or protected areas.
Conflict of interest
The auhtors declare that they have no conflict of interest.
Consent to participate
N/A.
Consent for publication
N/A.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Naznin, F., Hazarika, I., Laskar, D. et al. Mining association between different emotion classes present in users posts of social media. Soc. Netw. Anal. Min. 14, 76 (2024). https://doi.org/10.1007/s13278-024-01241-w
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s13278-024-01241-w