{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T17:25:29Z","timestamp":1790702729633,"version":"4.1.0"},"reference-count":35,"publisher":"Emerald","issue":"9","license":[{"start":{"date-parts":[[2018,9,5]],"date-time":"2018-09-05T00:00:00Z","timestamp":1536105600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IMDS"],"published-print":{"date-parts":[[2018,9,28]]},"abstract":"<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Purpose<\/jats:title>\n<jats:p>Recently, various Twitter Sentiment Analysis (TSA) techniques have been developed, but little has paid attention to the microblogging feature \u2013 emojis, and few works have been conducted on the multi-class sentiment analysis of tweets. The purpose of this paper is to consider the popularity of emojis on Twitter and investigate the feasibility of an emoji training heuristic for multi-class sentiment classification of tweets. Tweets from the \u201c2016 Orlando nightclub shooting\u201d were used as a source of study. Besides, this study also aims to demonstrate how mapping can contribute to interpreting sentiments.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Design\/methodology\/approach<\/jats:title>\n<jats:p>The authors presented a methodological framework to collect, pre-process, analyse and map public Twitter postings related to the shooting. The authors designed and implemented an emoji training heuristic, which automatically prepares the training data set, a feature needed in Big Data research. The authors improved upon the previous framework by advancing the pre-processing techniques, enhancing feature engineering and optimising the classification models. The authors constructed the sentiment model with a logistic regression classifier and selected features. Finally, the authors presented how to visualise citizen sentiments on maps dynamically using Mapbox.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Findings<\/jats:title>\n<jats:p>The sentiment model constructed with the automatically annotated training sets using an emoji approach and selected features performs well in classifying tweets into five different sentiment classes, with a macro-averaged <jats:italic>F<\/jats:italic>-measure of 0.635, a macro-averaged accuracy of 0.689 and the MAEM of 0.530. Compared to those experimental results in related works, the results are satisfactory, indicating the model is effective and the proposed emoji training heuristic is useful and feasible in multi-class TSA. The maps authors created, provide a much easier-to-understand visual representation of the data, and make it more efficient to monitor citizen sentiments and distributions.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Originality\/value<\/jats:title>\n<jats:p>This work appears to be the first to conduct multi-class sentiment classification on Twitter with automatic annotation of training sets using emojis. Little attention has been paid to applying TSA to monitor the public\u2019s attitudes towards terror attacks and country\u2019s gun policies, the authors consider this work to be a pioneering work. Besides, the authors have introduced a new data set of 2016 Orlando Shooting tweets, which will be made available for other researchers to mine the public\u2019s political opinions about gun policies.<\/jats:p>\n<\/jats:sec>","DOI":"10.1108\/imds-12-2017-0582","type":"journal-article","created":{"date-parts":[[2018,9,5]],"date-time":"2018-09-05T06:46:10Z","timestamp":1536129970000},"page":"1804-1820","source":"Crossref","is-referenced-by-count":47,"title":["Multi-class Twitter sentiment classification with emojis"],"prefix":"10.1108","volume":"118","author":[{"given":"Mengdi","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eugene","family":"Ch\u2019ng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alain Yee Loong","family":"Chong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon","family":"See","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"140","published-online":{"date-parts":[[2018,9,5]]},"reference":[{"key":"key2021041507210884300_ref001","first-page":"30","article-title":"Sentiment analysis of Twitter data","year":"2011"},{"issue":"1","key":"key2021041507210884300_ref002","doi-asserted-by":"crossref","first-page":"360","DOI":"10.17706\/IJCEE.2017.9.1.360-369","article-title":"The effects of emoji in sentiment analysis","volume":"9","year":"2017","journal-title":"International Journal of Computer and Electrical Engineering"},{"key":"key2021041507210884300_ref003","first-page":"85","article-title":"TwiSE at semeval-2016 task 4: Twitter sentiment classification","year":"2016"},{"key":"key2021041507210884300_ref004","article-title":"Robust sentiment detection on Twitter from biased and noisy data","year":"2010"},{"key":"key2021041507210884300_ref005","first-page":"2","article-title":"On using Twitter to monitor political sentiment and predict election results","year":"2011"},{"key":"key2021041507210884300_ref006","first-page":"1","article-title":"A pattern-based approach for multi-class sentiment analysis in Twitter","volume":"5","year":"2017","journal-title":"IEEE Access"},{"key":"key2021041507210884300_ref007","article-title":"The value of using big data technologies in computational social science","year":"2014"},{"issue":"1","key":"key2021041507210884300_ref008","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1007\/s10796-010-9273-x","article-title":"A microblogging-based approach to terrorism informatics: exploration and chronicling civilian sentiment and response to terrorism events via Twitter","volume":"13","year":"2011","journal-title":"Information Systems Frontiers"},{"key":"key2021041507210884300_ref009","first-page":"2493","article-title":"Natural language processing (almost) from scratch","volume":"12","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"key2021041507210884300_ref010","article-title":"IIIT-H at SemEval 2015: Twitter sentiment analysis the good, the bad and the neutral\u202f!","year":"2015"},{"issue":"3","key":"key2021041507210884300_ref011","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1111\/j.1468-2885.2010.01362.x","article-title":"Functions of the nonverbal in CMC: emoticons and illocutionary force","volume":"20","year":"2010","journal-title":"Communication Theory"},{"issue":"2","key":"key2021041507210884300_ref012","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2938640","article-title":"Like it or not: a survey of Twitter sentiment analysis methods","volume":"49","year":"2016","journal-title":"ACM Computing Surveys"},{"key":"key2021041507210884300_ref013","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/j.chb.2014.01.047","article-title":"Letter lepetitions in computer-mediated communication: a unique link between spoken and online language","volume":"34","year":"2014","journal-title":"Computers in Human Behavior"},{"key":"key2021041507210884300_ref014","first-page":"89","article-title":"Combining lexicon-based and learning-based methods for Twitter sentiment analysis","year":"2015","journal-title":"International Journal of Electronics, Communication and Soft Computing Science & Engineering, ATCON-2015 Special Issue, National Conference on \u201cAdvanced Technologies in Computing and Networking\u201d, ISSN: 2277-9477"},{"key":"key2021041507210884300_ref015","doi-asserted-by":"crossref","first-page":"723","DOI":"10.1613\/jair.4272","article-title":"Sentiment analysis of short informal texts","volume":"50","year":"2014","journal-title":"Journal of Artificial Intelligence Research"},{"key":"key2021041507210884300_ref016","article-title":"Twitter sentiment analysis: lexicon method, machine learning method and their combination","year":"2015"},{"key":"key2021041507210884300_ref017","first-page":"538","article-title":"Twitter sentiment analysis: the good the bad and the omg!","year":"2011"},{"key":"key2021041507210884300_ref018","article-title":"Put at semeval-2016 task 4: the ABC of Twitter sentiment analysis","year":"2016"},{"key":"key2021041507210884300_ref019","article-title":"Twitter sentiment analysis of the 2016 U.S. presidential election using an emoji training heuristic","year":"2016"},{"key":"key2021041507210884300_ref020","article-title":"The new eye of smart city: novel citizen sentiment analysis in Twitter","year":"2016"},{"issue":"1","key":"key2021041507210884300_ref022","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2200\/S00416ED1V01Y201204HLT016","article-title":"Sentiment analysis and opinion mining","volume":"5","year":"2012","journal-title":"Synthesis Lectures on Human Language Technologies"},{"key":"key2021041507210884300_ref021","first-page":"415","article-title":"A survey of opinion mining and sentiment analysis","year":"2012","journal-title":"Mining Text Data"},{"issue":"Part 2","key":"key2021041507210884300_ref023","first-page":"390","article-title":"Feature selection for Twitter sentiment analysis: an experimental study","volume":"7182","year":"2015","journal-title":"Computational Linguistics and Intelligent Text Processing"},{"issue":"4","key":"key2021041507210884300_ref024","doi-asserted-by":"crossref","first-page":"1093","DOI":"10.1016\/j.asej.2014.04.011","article-title":"Sentiment analysis algorithms and applications: a survey","volume":"5","year":"2014","journal-title":"Ain Shams Engineering Journal"},{"key":"key2021041507210884300_ref025","first-page":"1","article-title":"{SemEval}-2016 task 4: sentiment analysis in {T}witter","year":"2016"},{"key":"key2021041507210884300_ref026","article-title":"Language-independent Twitter sentiment analysis","year":"2012"},{"key":"key2021041507210884300_ref027","first-page":"1354","article-title":"Topic modeling based sentiment analysis on social media for stock market prediction","year":"2015"},{"issue":"12","key":"key2021041507210884300_ref028","first-page":"1","article-title":"Sentiment of emojis","volume":"10","year":"2015","journal-title":"Plos One"},{"key":"key2021041507210884300_ref029","first-page":"1320","article-title":"Twitter as a corpus for sentiment analysis and opinion mining","year":"2010"},{"key":"key2021041507210884300_ref030","first-page":"79","article-title":"Thumbs Up?: Sentiment classification using machine learning techniques","year":"2002"},{"key":"key2021041507210884300_ref031","article-title":"Emoticons vs emojis on Twitter: a causal inference approach","year":"2016"},{"key":"key2021041507210884300_ref032","first-page":"451","article-title":"SemEval-2015 task 10: sentiment analysis in Twitter","year":"2015"},{"key":"key2021041507210884300_ref033","article-title":"INSIGHT-1 at semeval-2016 task 4: convolutional neural networks for sentiment classification and quantification","year":"2016"},{"key":"key2021041507210884300_ref034","first-page":"79","article-title":"LyS at semeval-2016 task 4: exploiting neural activation values for Twitter sentiment classification and quantification","year":"2016"},{"key":"key2021041507210884300_ref035","unstructured":"Wikipedia (2016), \u201cOrlando nightclub shooting\u201d, available at: https:\/\/en.wikipedia.org\/wiki\/2016_Orlando_nightclub_shooting (accessed 3 May 2017)."}],"container-title":["Industrial Management &amp; Data Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IMDS-12-2017-0582\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IMDS-12-2017-0582\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T21:54:18Z","timestamp":1753394058000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/imds\/article\/118\/9\/1804-1820\/176230"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9,5]]},"references-count":35,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2018,9,5]]},"published-print":{"date-parts":[[2018,9,28]]}},"alternative-id":["10.1108\/IMDS-12-2017-0582"],"URL":"https:\/\/doi.org\/10.1108\/imds-12-2017-0582","relation":{},"ISSN":["0263-5577"],"issn-type":[{"value":"0263-5577","type":"print"}],"subject":[],"published":{"date-parts":[[2018,9,5]]}}}