While audience profiling has been a critical concern in social media marketing, little research has used a systematic methodology to identify fans and anti-fans in social media communities. This study aimed to develop a fan and anti-fan detection model by analysing social media users’ mood responses and comments on fan page posts. The sentiment analysis of comments was conducted using a bidirectional long short-term memory (LSTM) model. A total of 83 posts, 849,820 emoticons and 216,688 comments were collected from two different fan pages over 14 days. Results showed that the proposed model, combining emotional reaction analysis and sentiment analysis of their comments, exhibited better fan and anti-fan identification capability than the single-dimensional behaviour model. It exhibited 96% accuracy, 100% precision and 93% recall in terms of community management. This study provides a novel, accurate and efficient way to identify fans and anti-fans that can help form more targeted marketing strategies for social media managers in a cost-effective manner.
GiuntiniFTRuizLPKirchnerLDFet al. How do I feel? Identifying emotional expressions on Facebook reactions using clustering mechanism. IEEE Access2019; 7: 53909–53921.
2.
MostafaMM.More than words: social networks’ text mining for consumer brand sentiments. Expert Syst Appl2013; 40(10): 4241–4251.
3.
LeeYJWuCH.Effects of electronic word-of-mouth messages on consumers’ trust. Commun Manag Res2011; 10(2): 69–104.
4.
ReichheldFFSasserW.Zero defections: quality comes to services. Harv Bus Rev1990; 68(5): 105–111.
5.
LamDMizerskiD.The effects of locus of control on word of mouth communication. J Mark Commun2005; 11(3): 215–228.
6.
MangoldWGMillerFBrockwayGR.Word of mouth communication in the service marketplace. J Serv Mark1999; 13(1): 73–89.
7.
TyboutAMCalderBJSternthalB.Using information processing theory to design marketing strategy. J Mark Res1981; 18: 73–79.
8.
HajhmidaMBOueslatiO.Predicting mobile application breakout using sentiment analysis of Facebook posts. J Inf Sci2021; 47(4): 502–516.
9.
KimBJSinghVWinerRS.The Pareto rule for frequently purchased packaged goods: an empirical generalization. Mark Lett2017; 28(4): 491–507.
10.
LiewH.Anti-fandom in the Xiaxue empire: a celebrity blogger and her haters. J Fandom Stud2019; 7(3): 261–277.
11.
DeanJ.Celebritization from below: celebrity, fandom, and anti-fandom in British politics. New Political Sci2021; 43(3): 320–338.
12.
GrayJ.Antifandom and the moral text: television without pity and textual dislike. Am Behav Sci2005; 48(7): 840–858.
13.
NgE.Cancel culture, popular media, and fandom. In: Cancel culture. Cham: Palgrave Macmillan, 2022, pp. 13–17. DOI: 10.1007/978-3-030-97374-2_2.
14.
BasileACaselliTNissimM.Predicting controversial news using Facebook reactions. In: Proceedings of the fourth Italian conference on computational linguistics, Rome, 11–13 December 2017, pp. 11–17. DOI: 10.4000/books.aaccademia.2370.
15.
AnnamalaiBYoshidaMVarshneySet al. Social media content strategy for sport clubs to drive fan engagement. J Retail Consum Serv2021; 62: 102648.
16.
MirAASevukanR.Sentiment analysis of Indian Tweets about Covid-19 vaccines. J Inf Sci. Epub ahead of print 16September2022. DOI: 10.1177/01655515221118049.
17.
ChauhanPSharmaNSikkaG.The emergence of social media data and sentiment analysis in election prediction. J Ambient Intell Humaniz Comput2021; 12(2): 2601–2627.
18.
KaurWBalakrishnanVRanaOet al. Liking, sharing, commenting and reacting on Facebook: user behaviors’ impact on sentiment intensity. Telemat Inform2019; 39: 25–36.
19.
SailunazKAlhajjR.Emotion and sentiment analysis from Twitter text. J Comput Sci2019; 36: 101003.
20.
HauthalEBurghardtDDunkelA.Analyzing and visualizing emotional reactions expressed by emojis in location-based social media. ISPRS Int J Geo-inf2019; 8(3): 113–133.
21.
LoureiroMLAllóM.Sensing climate change and energy issues: sentiment and emotion analysis with social media in the U.K. And Spain. Energy Policy2020; 143: 111490.
22.
BarachiMEAlKhatibMMathewSet al. A novel sentiment analysis framework for monitoring the evolving public opinion in real-time: case study on climate change. J Clean Prod2021; 312: 127820.
23.
SahlabadiMMuniyandiRCShukurZ.Detecting abnormal behavior in social network websites by using a process mining technique. J Comput Sci2014; 10(3): 393–402.
24.
WangXSuiYTaoYet al. Detecting abnormal social network accounts with Hurst of interest distribution. Secur Commun Netw2021; 2021: 6653430.
25.
OueslatiWArramiSADhouiouiZet al. Opinion leaders’ detection in dynamic social networks. Concurr Comput Pract Exp2020; 33(1): 1–17.
26.
AleahmadAKarisaniPRahgozarMet al. OLFinder: finding opinion leaders in online social networks. J Inf Sci2016; 42(5): 659–674.
27.
SheikhahmadiANematbakhshMA.Identification of multi-spreader users in social networks for viral marketing. J Inf Sci2017; 43(3): 412–423.
28.
OrabiMMouhebDAlAghbariZet al. Detection of bots in social media: a systematic review. Inf Process Manage2020; 57(4): 102250.
29.
SahooSRGuptaBB.Real-time detection of fake account in Twitter using machine-learning approach. In: GaoXZTiwariSTrivediMCet al. (eds) Advances in computational intelligence and communication technology. Singapore: Springer, 2021, pp. 149–159.
30.
EllakyZBenabbouFOuahabiSet al. A survey of spam bots detection in online social networks. In: Proceedings of 2021 international conference on digital age and technological advances for sustainable development, Marrakech, Morocco, 29–30 June 2021, pp. 58–65. New York: IEEE.
31.
YongLCaiMQinSet al. Depressive emotion detection and behavior analysis of men who have sex with men via social media. Front Psychiatry2020; 11: 830–842.
32.
KramerADGuilloryJEHancockJT.Experimental evidence of massive-scale emotional contagion through social networks. Proc Natl Acad Sci2014; 111(24): 8788–8790.
33.
JensenJ.Fandom as pathology: the consequences of characterization. In: LewisL (ed.) The adoring audience: fan culture and popular media. London: Routledge, 1992, pp. 9–26.
34.
WallaceEBuilIde ChernatonyLet al. Who ‘likes’ you… and why? A typology of Facebook fans. J Advert Res2014; 54(1): 92–109.
35.
AwaHONwucheCA.Cognitive consistency in purchase behavior: theoretical & empirical analyses. Int J Psychol Stud2010; 2(3): 44–54.
36.
StavrosCMengMDWestbergKet al. Understanding fan motivation for interacting on social media. Sport Manag Rev2014; 17(4): 455–469.
37.
RoySKSharmaABoseSet al. Consumer – brand relationship: a brand hate perspective. J Bus Res2022; 144: 1293–1304.
38.
ChinCYLuHPWuCM.Facebook users’ motivation for clicking the ‘Like’ button. Soc Behav Pers2015; 43(4): 579–592.
39.
PoolCNissimM.Distant supervision for emotion detection using Facebook reactions. In: Proceedings of the workshop on computational modeling of people’s opinions, personality, and emotions in social media (W16-4304), Osaka, Japan, 12 December 2016, pp. 30–39, https://aclanthology.org/W16-4304
40.
BouldingWKalraAStaelinRet al. A dynamic process model of service quality: from expectations to behavioral intentions. J Mark Res1993; 30(1): 7–27.
41.
PoomkaPKerdprasopNKerdprasopK.Machine learning versus deep learning performances on the sentiment analysis of product reviews. Int J Mach Learn Comput2021; 11(2): 103–109.
42.
PriyaBG.Emoji based sentiment analysis using KNN. Int J Sci Res2019; 7(4): 859–865.
43.
TripathyAAgrawalARathSK.Classification of sentimental reviews using machine learning techniques. Procedia Comput Sci2015; 57: 821–829.
44.
TripathyAAgrawalARathSK.Classification of sentiment reviews using n-gram machine learning approach. Expert Syst Appl2016; 57: 117–126.
45.
XuGMengYQiuXet al. Sentiment analysis of comment texts based on BiLSTM. IEEE Access2019; 7: 51522–51532.
46.
YangSSunQZhouHet al. A multi-layer neural network model integrating BiLSTM and CNN for Chinese sentiment recognition. In: Proceedings of the 2018 international conference on computing and artificial intelligence, Chengdu, China, 12–14 March 2018.
47.
LópezWMerlinoJRodríguez-BoccaP.Learning semantic information from internet domain names using word embeddings. Eng Appl Artif Intell2020; 94: 103823.
48.
AlshariEMAzmanADoraisamySet al. SNTI2VEC: an effective feature extraction technique for sentiment analysis based on WORD2VEC. Malays J Comput Sci2020; 33(3): 240–251.
49.
BelcastroLBrandaFCantiniRet al. Analyzing voter behavior on social media during the 2020 US presidential election campaign. Soc Netw Anal Min2022; 12(1): 1–16.
50.
FowlerEFFranzMMMartinGJet al. Political advertising online and offline. Am Political Sci Rev2011; 115(1): 130–149.
51.
HsiaoYC.Change in voters’ candidate evaluation during a political campaign: a case study of the 2012 presidential election in Taiwan. Elect Stud2017; 24(2): 1–38.
52.
ZhouJLuYDaiHNet al. Sentiment analysis of Chinese microblog based on stacked bidirectional LSTM. IEEE Access2019; 7: 38856–38866.
