Sentiment Analysis Using Machine Learning Algorithms
Fatma Jemai, Mohamed Hayouni, Sahbi Baccar
Abstract
This work aims at building a classifier able of predicting the polarity of a comment while using Machine Learning (ML) algorithms. Our work is essentially divided into three tasks: data extraction, processing and modelling. In order to build our model, we use the NLTK dataset. Then, we use text mining techniques to generate and process the variables. Based on a supervised probabilistic machine learning algorithm, we tended to create a classifier to classify our tweets into positive and negative sentiments then we opt for two experiments to evaluate the performance of our model. Compered to previous reported works, we achieve greater precision.
Topics & Concepts
Computer scienceMachine learningArtificial intelligenceClassifier (UML)Probabilistic logicSentiment analysisAlgorithmLearning classifier systemData miningUnsupervised learningSentiment Analysis and Opinion MiningAdvanced Text Analysis TechniquesSpam and Phishing Detection