Skip to Main content Skip to Navigation
New interface
Journal articles

A hybrid multilingual fuzzy-based approach to the sentiment analysis problem using sentiwordnet

Youness Madani 1 Mohammed Erritali 1 Jamaa Bengourram 1 Francoise Sailhan 2 
2 CEDRIC - ROC - CEDRIC. Réseaux et Objets Connectés
CEDRIC - Centre d'études et de recherche en informatique et communications
Abstract : Sentiment Analysis or in particular social network analysis (SNA) is a new research area which is increased explosively. This domain has become a very active research issue in data mining and natural language processing. Sentiment analysis (opinion mining) consists in analyzing and extracting emotions, opinions or attitudes from product’s reviews, movie's reviews, etc., and classify them into classes such as positive, negative and neutral, or extract the degree of importance (polarity). In this paper, we propose a new hybrid approach for classifying tweets into classes based on fuzzy logic and a lexicon based approach using SentiWordnet. Our approach consists in classifying tweets according to three classes: positive, negative or neutral, using SentiWordNet and the fuzzy logic with its three important steps: Fuzzification, Rule Inference/aggregation, and Defuzzification. The dataset of tweets to classify and the result of the classification are stored in the Hadoop Distributed File System (HDFS), and we use the Hadoop MapReduce for the application of our proposal.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03466148
Contributor : Francoise Sailhan Connect in order to contact the contributor
Submitted on : Wednesday, April 13, 2022 - 2:31:52 PM
Last modification on : Wednesday, September 28, 2022 - 5:59:53 AM
Long-term archiving on: : Thursday, July 14, 2022 - 6:39:15 PM

File

Fuzzy_Sentiment_HALL1-2.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Youness Madani, Mohammed Erritali, Jamaa Bengourram, Francoise Sailhan. A hybrid multilingual fuzzy-based approach to the sentiment analysis problem using sentiwordnet. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 2020, 28 (3), pp.361-390. ⟨10.1142/S0218488520500154⟩. ⟨hal-03466148⟩

Share

Metrics

Record views

57

Files downloads

11