Improving relationship management in universities with sentiment analysis and topic modeling of social media channels: learnings from UFPA

Online Social networking (OSN) platforms such as Facebook, daily have a massive number of users and content being created. Users of such services have the power to share opinions and influence others. This creates an interesting scenario, where brands and institutions can have a digital presence to interact directly with their target audience. Universities around the world are also using those platforms for reaching out their students and staff, acting as a new channel for services and public relations. Social Customer Relationship Management (SCRM) principles can be applied in this scenario, for universities, and help them on the management of this relationship with their public. Thus, this work aims to apply SCRM methodology for a university Facebook fan page, through techniques of Sentiment Analysis (SA) and topic modeling (TM) using Latent Dirichlet Allocation, in order to find topics people are complimenting or complaining about in their comments. The main goal is to improve SCRM processes through the results and insights provided by those techniques. The final discussion with the communications professionals from UFPA university has revealed the experiments and insights provided in this work are valuable for their social media (SM) management workflow.

[1]  Barbara J. Grosz,et al.  Natural-Language Processing , 1982, Artificial Intelligence.

[2]  J. Radcliffe,et al.  Eight Building Blocks of CRM : A Framework for , 2001 .

[3]  Bo Pang,et al.  Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

[4]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[5]  Hanna M. Wallach,et al.  Topic modeling: beyond bag-of-words , 2006, ICML.

[6]  Seok Kang,et al.  Colleges and universities’ use of the World Wide Web: A public relations tool for the digital age☆ , 2006 .

[7]  Ralf Krestel,et al.  Latent dirichlet allocation for tag recommendation , 2009, RecSys '09.

[8]  Rudy Prabowo,et al.  Sentiment analysis: A combined approach , 2009, J. Informetrics.

[9]  Farzana Shafique,et al.  Exploitation of social media among university students: A case study , 2010, Webology.

[10]  David M. Blei,et al.  Probabilistic topic models , 2012, Commun. ACM.

[11]  Brian D. Davison,et al.  Empirical study of topic modeling in Twitter , 2010, SOMA '10.

[12]  Victoria L. Crittenden,et al.  We're all connected: The power of the social media ecosystem , 2011 .

[13]  Maite Taboada,et al.  Lexicon-Based Methods for Sentiment Analysis , 2011, CL.

[14]  Rainer Alt,et al.  Social Customer Relationship Management: State of the Art and Learnings from Current Projects , 2012, Bled eConference.

[15]  Sam H. Dekay.  How large companies react to negative Facebook comments , 2012 .

[16]  Reynol Junco,et al.  The relationship between frequency of Facebook use, participation in Facebook activities, and student engagement , 2012, Comput. Educ..

[17]  Ioan Toma,et al.  An approach for evaluation of social media monitoring tools , 2012 .

[18]  Rainer Alt,et al.  Social-Customer-Relationship-Management (Social-CRM) , 2012, Wirtschaftsinf..

[19]  Eugene Agichtein,et al.  TM-LDA: efficient online modeling of latent topic transitions in social media , 2012, KDD.

[20]  Charu C. Aggarwal,et al.  Mining Text Data , 2012, Springer US.

[21]  Nicholas J. Kelling,et al.  The tweets that killed a university: A case study investigating the use of traditional and social media in the closure of a state university , 2013, Comput. Hum. Behav..

[22]  Anil Kumar,et al.  The value of social media: are universities successfully engaging their audience? , 2013 .

[23]  C. Baird,et al.  From social media to social customer relationship management , 2013, IEEE Engineering Management Review.

[24]  M. Shamim Hossain,et al.  Social Event Classification via Boosted Multimodal Supervised Latent Dirichlet Allocation , 2015, ACM Trans. Multim. Comput. Commun. Appl..

[25]  David Valle Cruz,et al.  Social media effect inside university communication: a Mexican case , 2014, 2014 International Conference on Education Technologies and Computers (ICETC).

[26]  M. Grossi,et al.  A utilização das tecnologias digitais de informação e comunicação nas redes sociais pelos universitários brasileiros , 2014 .

[27]  Michal Karpowicz,et al.  Computational approaches for mining user's opinions on the Web 2.0 , 2014, Inf. Process. Manag..

[28]  Kiyoaki Shirai,et al.  Topic Modeling based Sentiment Analysis on Social Media for Stock Market Prediction , 2015, ACL.

[29]  Chia-Yen Chen,et al.  News topics categorization using latent Dirichlet allocation and sparse representation classifier , 2015, 2015 IEEE International Conference on Consumer Electronics - Taiwan.

[30]  C. A. Alves.  Gestão da comunicação das Universidades Federais: mapeamento das ações e omissões , 2015 .

[31]  Jorge A. Balazs,et al.  Opinion Mining and Information Fusion: A survey , 2016, Inf. Fusion.

[32]  Fabrício Benevenuto,et al.  A Benchmark Comparison of State-of-the-Practice Sentiment Analysis Methods , 2015, ArXiv.

[33]  Fabrício Benevenuto,et al.  iFeel 2.0: A Multilingual Benchmarking System for Sentence-Level Sentiment Analysis , 2021, ICWSM.

[34]  R. Jung,et al.  Social Customer Relationship Management , 2016 .

[35]  Stefan Feuerriegel,et al.  Analysis of How Underlying Topics in Financial News Affect Stock Prices Using Latent Dirichlet Allocation , 2016, 2016 49th Hawaii International Conference on System Sciences (HICSS).

[36]  Jui-Feng Yeh,et al.  Topic detection and tracking for conversational content by using conceptual dynamic latent Dirichlet allocation , 2016, Neurocomputing.

[37]  Olaf Reinhold,et al.  Social CRM: Biggest Challenges to Make it Work in the Real World , 2016, BIS.

[38]  Yue Guo,et al.  Mining Meaning from Online Ratings and Reviews : Tourist Satisfaction Analysis Using Latent Dirichlet Allocation , 2016 .

[39]  L. L. Presti,et al.  Social Media Mix in the University Communication Plan: A Bridge Towards Public Engagement: Structured Abstract , 2016 .

[40]  Philipp Koehn,et al.  Synthesis Lectures on Human Language Technologies , 2016 .

[41]  Vincenzo Moscato,et al.  Probabilistic Approaches for Sentiment Analysis: Latent Dirichlet Allocation for Ontology Building and Sentiment Extraction , 2016, Sentiment Analysis and Ontology Engineering.

[42]  Lei Zhang,et al.  Sentiment Analysis and Opinion Mining , 2017, Encyclopedia of Machine Learning and Data Mining.

[43]  Shiliang Sun,et al.  A review of natural language processing techniques for opinion mining systems , 2017, Inf. Fusion.