Sentiment Expression via Emoticons on Social Media

Authors: Hao Wang, Jorge A. Castanon

Submitted to arXiv on 09 Nov. 2015
Abstract

Emoticons (e.g., :) and :( ) have been widely used in sentiment analysis and other NLP tasks as features to ma- chine learning algorithms or as entries of sentiment lexicons. In this paper, we argue that while emoticons are strong and common signals of sentiment expression on social media the relationship between emoticons and sentiment polarity are not always clear. Thus, any algorithm that deals with sentiment polarity should take emoticons into account but extreme cau- tion should be exercised in which emoticons to depend on. First, to demonstrate the prevalence of emoticons on social media, we analyzed the frequency of emoticons in a large re- cent Twitter data set. Then we carried out four analyses to examine the relationship between emoticons and sentiment polarity as well as the contexts in which emoticons are used. The first analysis surveyed a group of participants for their perceived sentiment polarity of the most frequent emoticons. The second analysis examined clustering of words and emoti- cons to better understand the meaning conveyed by the emoti- cons. The third analysis compared the sentiment polarity of microblog posts before and after emoticons were removed from the text. The last analysis tested the hypothesis that removing emoticons from text hurts sentiment classification by training two machine learning models with and without emoticons in the text respectively. The results confirms the arguments that: 1) a few emoticons are strong and reliable signals of sentiment polarity and one should take advantage of them in any senti- ment analysis; 2) a large group of the emoticons conveys com- plicated sentiment hence they should be treated with extreme caution.

The papers around it, by date and closeness

Higher is closer to this paper; left is older. Lines join papers close to each other: groups of lines are sub-topics. Select a point to see why it is there. Back to the summary of this paper

How to read this map? Illustrated guide

Closest papers Prior work it builds on Papers that cite it

Papers around this one

Ranked by how close their title and abstract are to this paper’s. Select some to read them together.

Closest papers

  1. Very close Same question Cites this paper
    Sentiment Expression via Emoticons on Social Media- Twitter
    Amritkumar Tupsoundarya · 2018 · International Journal for Research in Applied Science and Engineering Technology · cited 3 times · Not summarized yet

    Sentiment Expression via Emoticons on Social Media- Twitter discusses how emoticons signal sentiment in social media and urges caution about their polarity.

    Abstract

    : Extensive use of emoticons such as :) :-) ;) :D :( in the "social media" have drawn attentions of researchers for using them widely in sentiment analysis and other “Natural Language Processing (NLP)” tasks as features entries of sentiment lexicons or to “machine learning algorithms”. Although emoticons are a common and strong sign of expression of feelings/sentiments in social platforms, the relation between expression of sentiments and emoticons is not always clear & hence both must be included to draw nearly exact sentiment. Therefore, any such algorithm that deals with expressing the sentiment must take emoticons into account but one has to be extremely careful with the emoticons that a…

  2. Very close* Same question Cites this paper
    Emoticons and Their Effects on Sentiment Analysis of Twitter Data
    Padma S. Dandannavar, S. Mangalwede, S. Deshpande · 2019 · EAI International Conference on Big Data Innovation for Sustainable Cognitive Computing · cited 12 times · Not summarized yet

    Emoticons and Their Effects on Sentiment Analysis of Twitter Data examines emoticons’ role in Twitter sentiment analysis.

  3. Very close Another approach to the problem Cited by this paper
    Using Emoticons to Reduce Dependency in Machine Learning Techniques for Sentiment Classification
    Jonathon Read · 2005 · Annual Meeting of the Association for Computational Linguistics · cited 647 times · Not summarized yet

    Using Emoticons to Reduce Dependency in Machine Learning Techniques for Sentiment Classification uses emoticon-labeled training data to address domain, topic, and time dependence.

    Abstract

    Sentiment Classification seeks to identify a piece of text according to its author's general feeling toward their subject, be it positive or negative. Traditional machine learning techniques have been applied to this problem with reasonable success, but they have been shown to work well only when there is a good match between the training and test data with respect to topic. This paper demonstrates that match with respect to domain and time is also important, and presents preliminary experiments with training data labeled with emoticons, which has the potential of being independent of domain, topic and time.

  4. Very close* Same question
    Role of Emoticons for Multidimensional Sentiment Analysis of Twitter
    Yuki Yamamoto, Tadahiko Kumamoto, Akiyo Nadamoto · 2014 · International Conference on Information Integration and Web-based Applications & Services · cited 35 times · Not summarized yet

    Role of Emoticons for Multidimensional Sentiment Analysis of Twitter examines emoticons in Twitter sentiment analysis.

  5. Very close Same question Cites this paper
    Sentimental Analysis based on Text and Emoticons
    A. Sastry, K. Veera, Venkata Anudeep et al. · 2020 · International Journal of Innovative Technology and Exploring Engineering · cited 1 time · Not summarized yet

    Sentimental Analysis based on Text and Emoticons studies sentiment analysis using informal text and emoticons in social media.

    Abstract

    Long range informal communication has bit by bit become an everyday practice for individuals to post their feelings, perspectives and remarks on any item or individual. Individuals share their sentiments online in an exceptionally casual language. Along these lines, it is exceptionally troublesome errand to break down precise slants connected with that common language. Estimation Analysis is an investigation of individuals' mentality, assessments, and feelings to arrange whether it is certain, negative or impartial. Utilization of emojis via web-based networking media has expanded quickly as of late. Subsequently, we have concentrated more on how emojis assume a significant job in opinion ex…

  6. Very close* Same question
    Effectiveness of Social Media Sentiment Analysis Tools with the Support of Emoticon/Emoji
    Duncan C. Peacock, Habib Ullah Khan · 2019 · International Conference on Information Technology: New Generations · cited 12 times · Not summarized yet

    Effectiveness of Social Media Sentiment Analysis Tools with the Support of Emoticon/Emoji concerns emoticons and emojis in social-media sentiment analysis.

  7. Very close Same question Cites this paper
    Understanding Emojis for Sentiment Analysis
    Byungjoon Yoo, Julia Taylor Rayz · 2021 · The Florida AI Research Society · cited 16 times · Not summarized yet

    Understanding Emojis for Sentiment Analysis analyzes emoji use in tweets and its effects on tweet sentiment classification.

    Abstract

    Many people use emojis to express themselves in a more clear and efficient way and the usage of such expressions has grown significantly. In recent years, there have been many research papers that analyze the meanings of individual emojis or show the accuracy of sentiment analysis when emojis are included. However, there is limited research done on understanding how emojis are used to show sentiment and how it affects sentiment analysis. In this paper, we analyze the usage of emojis in Tweets and their effects on the overall sentiment of the Tweet. We also introduce a pre-processing method for emojis that increases the effect of emojis and as a result, improves the sentiment analysis accurac…

  8. Very close* Same question
    Exploiting emoticons in sentiment analysis
    Alexander Hogenboom, Daniella Bal, Flavius Frasincar et al. · 2013 · ACM Symposium on Applied Computing · cited 243 times · Not summarized yet

    Exploiting emoticons in sentiment analysis addresses using emoticons as signals for sentiment analysis.

Prior work it builds on

  1. Close* Broader context
    Microblogging Sentiment Analysis Using Emotional Vector
    Lumin Zhang, Yande Jia, Bin Zhou et al. · 2012 · 2012 Second International Conference on Cloud and Green Computing · cited 17 times · Not summarized yet

    Microblogging Sentiment Analysis Using Emotional Vector studies sentiment analysis in microblogs using an emotional-vector approach.

  2. Close Broader context
    Twitter Sentiment Analysis: The Good the Bad and the OMG!
    Efthymios Kouloumpis, Theresa Wilson, J. Moore · 2011 · International Conference on Web and Social Media · cited 1,336 times · Not summarized yet

    Twitter Sentiment Analysis: The Good the Bad and the OMG! evaluates linguistic features and lexical resources for detecting sentiment in Twitter messages.

    Abstract

    In this paper, we investigate the utility of linguistic features for detecting the sentiment of Twitter messages. We evaluate the usefulness of existing lexical resources as well as features that capture information about the informal and creative language used in microblogging. We take a supervied approach to the problem, but leverage existing hashtags in the Twitter data for building training data.

  3. Close* Same method, another problem
    MoodLens: an emoticon-based sentiment analysis system for chinese tweets
    Ji-Chang Zhao, Li Dong, Jun-Jie Wu et al. · 2012 · Knowledge Discovery and Data Mining · cited 272 times · Not summarized yet

    MoodLens: an emoticon-based sentiment analysis system for chinese tweets applies emoticon-based sentiment analysis to Chinese tweets.

  4. Related* Broader context
    Unsupervised sentiment analysis with emotional signals
    Xia Hu, Ji-Liang Tang, Hui-Ji Gao et al. · 2013 · The Web Conference · cited 421 times · Not summarized yet

    Unsupervised sentiment analysis with emotional signals studies sentiment analysis using emotional signals.

  5. Related Broader context
    From Tweets to Polls: Linking Text Sentiment to Public Opinion Time Series
    Brendan T. O'Connor, R. Balasubramanyan, Bryan R. Routledge et al. · 2010 · International Conference on Web and Social Media · cited 2,183 times · Not summarized yet

    From Tweets to Polls: Linking Text Sentiment to Public Opinion Time Series connects Twitter text sentiment with consumer-confidence and political-opinion polls.

    Abstract

    We connect measures of public opinion measured from polls with sentiment measured from text. We analyze several surveys on consumer confidence and political opinion over the 2008 to 2009 period, and find they correlate to sentiment word frequencies in contempora- neous Twitter messages. While our results vary across datasets, in several cases the correlations are as high as 80%, and capture important large-scale trends. The re- sults highlight the potential of text streams as a substi- tute and supplement for traditional polling. consumer confidence and political opinion, and can also pre- dict future movements in the polls. We find that temporal smoothing is a critically important issue to supp…

Papers that cite it

  1. Close* Same question Uses this paper in depth
    SentiReview: Sentiment analysis based on text and emoticons
    Payal Yadav, Dhatri Pandya · 2017 · International Conference on Innovative Mechanisms for Industry Applications · cited 37 times · Not summarized yet

    SentiReview: Sentiment analysis based on text and emoticons concerns sentiment analysis using both text and emoticons.

  2. Close Same question Uses this paper in depth
    How Do I Feel? Identifying Emotional Expressions on Facebook Reactions Using Clustering Mechanism
    F. Giuntini, Larissa Pires Ruiz, Luziane de Fátima Kirchner et al. · 2019 · IEEE Access · cited 43 times · Not summarized yet

    How Do I Feel? Identifying Emotional Expressions on Facebook Reactions Using Clustering Mechanism tests whether Facebook reactions express users’ intended emotional polarity and basic emotions.

    Abstract

    The recognition of emotions and feelings through computer technology and devices has been widely explored in recent years. Social networks have become a natural environment in which users express their feelings and opinions through social media, and this includes their Facebook reactions. The aim of this study was to investigate whether the emoticons have chosen by users in social network news actually express the emotions they wish to express, having as indicative, the polarity of the emotions, and the six basic emotions. The data collection was carried out following three courses of action: 1) survey of the posts with higher reactions rates of popular news pages; 2) selection of news by a …

  3. Close* Broader context
    Emoticon and Text Sarcasm Detection in Sentiment Analysis
    Shaina Gupta, Ravinder Singh, Varun Singla · 2019 · First International Conference on Sustainable Technologies for Computational Intelligence · cited 11 times · Not summarized yet

    Emoticon and Text Sarcasm Detection in Sentiment Analysis addresses sarcasm detection using emoticons and text.

  4. Very close* Review
    Multiclass Sentiment Analysis in Text and Emoticons of Twitter Data: A Review
    N. Babu, Fabeela Ali Rawther · 2021 · Not summarized yet

    Multiclass Sentiment Analysis in Text and Emoticons of Twitter Data: A Review reviews multiclass sentiment analysis using Twitter text and emoticons.

  5. Close Same method, another problem
    Unsupervised Sentiment Classification of Twitter Data using Emoticons
    Savitha B. Hiremath, S. Manjula, V. R. · 2021 · 2021 International Conference on Emerging Smart Computing and Informatics (ESCI) · cited 6 times · Not summarized yet

    Unsupervised Sentiment Classification of Twitter Data using Emoticons uses emoticons or emojis as emotion tokens for unsupervised tweet classification.

    Abstract

    Twitter is a powerful social media where people share their opinion on various topics. Sentiment Analysis on twitter data gives the classification of opinion on a topic as positive, negative or neutral. Twitter messages are written informally and tweets are short. Hence, the classification of tweets by only considering the text part of the message does not give accurate results. To improve the classification accuracy we use Emotion Tokens like Emoticons or Emojis. Emotion Tokens are independent of language, grammar or size of the tweet. Considering Emotion tokens while classifying tweets will improve the accuracy of classification. In this paper, we propose unsupervised Sentiment classificat…

How are these papers found?

We compare the title and abstract of this paper with those of every paper summarized on this site, and with the papers Semantic Scholar recommends, those it cites and those citing it (for a much-cited paper, its most recent citations and, from OpenAlex, the most cited ones). Among the prior work and the follow-ups, the papers that use each other in depth, a method it uses and the much-cited follow-ups come a little higher. The levels (very close, close, related) come from the similarity of the texts, not from a judgment of quality; * marks a paper without an abstract, compared by its title. The sentence under a paper is written by an AI from the two abstracts: check it in the papers. A paper marked not relevant by three readers leaves the list.

Updated on 4 November 2026.

The illustrated guide to the papers around a paper