Big Data Analytics for Opinion Mining and Patterns Detection of the Tunisian Election Zeineb Dhouioui Bestmod Laboratory ISG Tunis University of Tunis zeineb.dhouioui@hotmail.fr Hanen Bouali Bestmod Laboratory ISG Tunis University of Tunis hanene.bouali@gmail.com Jalel Akaichi Bestmod Laboratory ISG Tunis University of Tunis j.akaichi@gmail.com Abstract Big Data refers to an enormous vol- ume of structured and unstructured data that cannot be handled with traditional databases. The emergence of big data is due to the huge quantities of informa- tion. Currently, researchers tend to study big data particularly data produced from social networks. Nowadays, these latest become a vital and crucial tool in track- ing and extracting public opinion for de- veloped countries offering benefits to the democratic process of election. In this paper, we aim to identify the political preferences and tendency of the Tunisian population using classification and opin- ion mining techniques. To prove the use- fulness of the proposed method, we an- alyze electoral data sets in Tunisia ob- tained from the official sites of indepen- dent higher instance for election. This analysis demonstrates close correspon- dence between election results and ex- tracted opinion. 1 Introduction Big data is an extensively used term in tremen- dous data miscellany. Thus, this huge amount of data makes hard and sometimes impossible the analysis in a comfortable way using traditional data processing techniques (Anjaria and Guddeti, 2014). The dares includes pattern recognition, analysis, prediction ... Given the benefits of big data, they afford a chance to understand collected data in order to predict data patterns. With mil- lions of people using social networks to express their opinions, a tremendous volume of data is generated. Unfortunately, elections data that was published by the ISIE present only a summary of the vote counts. Detailed data is not accessible. Combining social networks data and ISIE data, voter behavior can be defined. (Sudhahar et al., 2015) With the evolution of the web 2.0 and the large number of users, big data analysis becomes very useful in pattern detection. Particularly, we han- dle in this paper Tunisian Voters in legislative and presidential election. Indeed, despite the mu- tual relation between socio-economic character- istics and voters in Tunisian elections, for the best of our knowledge, no researchers treat this task. Moreover, Elections in countries on path to democracy are considered as a source of enor- mous quantity of data. The exponential rise of social networks popu- larity influences real-world politics. These plat- forms have been exploited in Arab revolution as a mobilization tool and showing social move- ments. Moreover, social networks are used to study voters preferences in order to forecast elec- 157