Twitter is a social networking platform where users can create, view, and interact with short messages known as “tweets.” This large volume of user-generated content can be utilized by organizations, such as businesses, to understand customer opinions and attitudes. This research paper focuses on the use of emoticons in social media and the emotions they express. The aim of the study is to present a framework for analyzing emotional responses in real-world Twitter data. The proposed approach is based on supervised machine learning techniques and uses data collected through the “TWEEPY” crawler for experimental analysis. The gathered dataset is preprocessed and refined before being applied to different supervised models. Finally, each tweet is classified according to the emotional sentiment of the user, categorized as positive, negative, or neutral.

This study investigates the use of emoticon characters on social media platforms, especially within informal online communities. It empirically explores how emoticons influence text mining outcomes and how they relate to expressed emotions. The analysis covers a range of globally trending topics to identify whether differences exist between emotions conveyed through emoticons and those expressed in accompanying text. The results show that including emoticons in emotion analysis improves the overall sentiment scoring. Although emoji characters can represent both positive and negative emotions, the findings suggest that emoticons tend to enhance the expression of positive sentiment and lead to higher emotional scores compared to negative sentiment. For data collection, a crawler was used to extract tweets from Twitter, which were then processed through feature removal during the retrieval phase. Sentiment analysis has been applied for more than a decade, and it is now widely used by organizations as a support tool for decision-making and strategic planning. Its growing importance is also supported by advancements in data storage, accessibility, and processing enabled by big data technologies. Emoji analysis provides a new dimension to traditional text-based sentiment analysis. Since emojis are often used alongside text to add emphasis or context, examining the relationship between textual content and emojis is essential for a more complete understanding of emotions in online social networks.

[1]Yogesh Chandra, Antoreep Jana, “Sentiment Analysis using Machine Learning and Deep Learning”, 7th International Conference on Computing for Sustainable Global Development (INDIACom),2020. [2]M. SalehAlzubaidi and F. Bourennani, “Sentiment analysis of tweets usingemojis and texts,” in ACM International Conference Proceeding Series, ACM, Mar. 2021, pp. 111–114, doi: 10.1145/3459955.3460608. [3]S. E. Lee, D. Jeong, and E. Park, “MultiEmo: Multi-task framework for emoji prediction,” Knowledge-Based Systems, vol. 242, Art. no. 108437, Apr. 2022, doi: 10.1016/j.knosys.2022.108437 [4]Subhashini L, Li Y, Zhang J, Atukorale AS and Wu Y, “Mining and classifying customer reviews: a survey”, Artificial intelligence Review 54:6343–6389, 2021. [5]Mowlaei ME, Abadeh MS, Keshavarz H, “Aspect-based sentiment analysis using adaptive aspect based lexicons”, Expert System Application, 148:113234, 2020. [6]Kumar KN, Uma V, “intelligent sentiment-based lexicon for context-aware sentiment analysis: optimized neural network for sentiment classification on social media”, Journal of, 2021. [7]Zvarevashe K, Olugbara OO (2018),”A framework for sentiment analysis with opinion mining of hotel reviews”, In: 2018 Conference on information communications technology and society (ICTAS).IEEE, pp 1–4 [8]MayurWankhade, Annavarapu Chandra SekharaRao, ChaitanyaKulkarni,” A survey on sentiment analysis methods, applications, and challenges”, Artificial Intelligence Review ,2022. [9]CH. RayalaVinod Kumar, D. LalithaBhaskari, P. SrinivasaRao, “VLS Algorithm: A New Approach to Sentiment Analysis”, International Journal of Technology and research, Vol 9, Issue 05, MAY 2020, ISSN 2277-8616. [10]Kralj Novak, P., Smailović, J., Sluban, B., and Mozetič and I.,” Sentiment of emojis”, PLOS One, 10(12), 2015. [11]M. Fernández-Gavilanes, E. Costa-Montenegro, S. García-Méndez, F. J. González-Castaño, and J. Juncal-Martínez, “Evaluation of online emoji description resources for sentiment analysis purposes,” Expert Systems with Applications, vol. 184, Art.no. 115279, Dec. 2021, doi: 10.1016/j.eswa.2021.115279. [12] V. A. Pfeifer, E. L. Armstrong, and V. T. Lai, “Do all facial emojis communicate emotion? The impact of facial emojis on perceived sender emotion and text processing,” Computers in Human Behavior, vol. 126, p. 107016, Jan. 2022, doi: 10.1016/j.chb.2021.107016.

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close