A Credibility and Classification-Based Approach for Opinion Analysis in Social Networks

Lobna Azaza (1) , Fatima Zohra Ennaji, (2) , Zakaria Maamar (3) , El Fazziki Abdelaziz (2) , Marinette Savonnet (1) , Mohamed Sadgal, (2) , Eric Leclercq (1) , Idir Amine Amarouche (4) , Djamal Benslimane (5)

1 Le2i - Laboratoire Electronique, Informatique et Image [UMR6306]
2 LISI Lab., Université de Marrakecch
3 CITZU - CIT, Zayed University, Dubai
4 USTHB - Université des Sciences et de la Technologie Houari Boumediene = University of Sciences and Technology Houari Boumediene [Alger]
5 SOC - Service Oriented Computing

There is an ongoing interest in examining users' experiences made available through social media. Unfortunately these experiences like reviews on products and/or services are sometimes conflicting and thus, do not help develop a concise opinion on these products and/or services. This paper presents a multi-stage approach that extracts and consolidates reviews after addressing specific issues such as user multi-identity and user limited credibility. A system along with a set of experiments demonstrate the feasibility of the approach.

Mots clés: Social media; Reputation; Credibility; Opinion; Multi-identity

Domaines: Informatique [cs]; Informatique [cs]; Recherche d'information [cs.IR]

Lobna Azaza, Fatima Zohra Ennaji,, Zakaria Maamar, El Fazziki Abdelaziz, Marinette Savonnet, et al.. A Credibility and Classification-Based Approach for Opinion Analysis in Social Networks. 6th International Conference on Model and Data Engineering (MEDI), Sep 2016, Almeria, Spain. pp.303-316 ⟨10.1007/978-3-319-45547-1_24⟩. ⟨hal-01442692⟩