Survey of Sentiment analysis in Social networks

6-7 juin 2019
La Faculté des Sciences Juridiques, Economiques et Sociales Aïn Chock (FSJES-AC) - Casablanca (Maroc)
Abstract Nowadays, several platforms on the web and social networks like Facebook, Twitter, IMDB (Internet Movie Database) propose to file opinions, share feelings and opinions on a variety of topics. This information is very important in several fields like policy [1], digital marketing, social or individual, and their analysis allow as to extract opinions and to determine the subjective information contained in the texts. However, the automatic detection of opinions and the analysis of feelings are confronted with problems that distinguish it from traditional thematic research, because the sentiment is expressed in a very varied and very subtle way. In this paper we present an state of art of different researches conducted in the last four years on sentiment analysis in social networks. Our comparative study takes into account the data source and size, the preprocessing steps, the opinion classification approaches and the validation process. We can classify the sentiment analysis approaches on three: Lexicon or dictionary based approaches [2], Ontology based analysis [3] and Machine learning based ones [4][5]. Moreover, we notice that the most classification techniques used are Naïve Bye algorithm and SVM (support vector machine). Form data set point of view, we have found that the most analyzed social media platform is Twitter. The English language has the greatest number of sentiment analysis studies, while research is more limited for other languages including Arabic. References [1] Widodo Budiharto, Meiliana,” Prediction and analysis of Indonesia Presidential election from Twitter using sentiment analysis”, Journal of Big Data (2018) 5:51, https://doi.org/10.1186/s40537-018-0164-1, Springer. 2018. [2] N. A. Abdulla, N. A. Ahmed, M. A. Shehab, and M. Al-Ayoub, “Arabic sentiment analysis: Lexicon-based and corpus-based”, Conference: Applied Electrical Engineering and Computing Technologies (AEECT), DOI: 10.1109/AEECT.2013.6716448, IEEE Jordan Conference 2013. [3] Samir Tartir, Ibrahim Abdul-Nabi, Semantic Sentiment Analysis in Arabic Social Media , Journal of King Saud University - Computer and Information Sciences archive, Vol. 29 Issue 2, April 2017. [4]. Alayba, Abdulaziz M., et al. "Arabic language sentiment analysis on health services." Arabic Script Analysis and Recognition (ASAR), 2017 1st International Workshop on. IEEE, 2017. [5] Abbes, Mariem, Zied Kechaou, and Adel M. Alimi. "Enhanced Deep Learning Models for Sentiment Analysis in Arab Social Media." International Conference on Neural Information Processing. Springer, Cham, 2017.
Discipline scientifique : Informatique

Lieu de la conférence
Personnes connectées : 126 |  Contact |  À propos |  RSS
Sitemap