Importance of the Neutral Category in Fuzzy Clustering of Sentiments

Lawrence Nderu (1) , Nicolas Jouandeau (2) , Herman Akdag (2)

1 JKUAT - Jomo Kenyatta University of Agriculture and Technology
2 LIASD - Laboratoire d'Informatique Avancée de Saint-Denis

Social media is said to have an impact on the public discourse and communication in the society. It is increasingly being used in the political context. Social networks sites such as Facebook, Twitter and other microblogging services provide an opportunity for public to give opinions about some issues of interest. Twitter is an ideal platform for users to spread not only information in general but also political opinions, whereas Facebook provides the capability for direct dialogs. A lot of studies have shown that a need exists for stakeholders to collect, monitor, analyze, summarize and visualize these social media views. Some authors have tended to categorize these comments as either positive or negative ignoring the neutral category. In this paper, we demonstrate the importance of the neutral category in the clustering of sentiments from the social media. We then demonstrate the use of fuzzy clustering for this kind of task.

Mots clés: Sentiments Analysis; Fuzzy Clustering; Social Media; Neutral Category; Unsupervised Classification

Domaines: Intelligence artificielle [cs.AI]

Lawrence Nderu, Nicolas Jouandeau, Herman Akdag. Importance of the Neutral Category in Fuzzy Clustering of Sentiments. International Journal of Fuzzy Logic and Intelligent Systems, 2014, 4 (2), pp.1-6. ⟨10.5121/ijfls.2014.4201⟩. ⟨hal-02317142⟩