Investigating sentiment analysis using machine learning approach
Authors:
- 1 December 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 87-92
Abstract
Sentiment Analysis is an approach of studying people's emotions and sentiments based on a particular topic, service, event and it attributes. Sentiment analysis appears as a part of various business analysis systems to find opinions about their services or products. Both the availability of CPU resources and enormous amount of data generated by the users makes sentiment analysis an active research field in upcoming years. Most of the existing approaches focus on efficient feature extraction, at the same time some approaches focus on extracting semantic features, which makes mush contribution to sentiment analysis. This review paper gives a comprehensive overview on Sentiment analysis using NLP (Natural Language Processing) techniques. First, we start with some NLP techniques which are generally needed for preprocessing the input data. Second, we introduce various approaches and some problems related to sentiment analysis and discuss some challenges and problem in sentiment analysis. Finally, we illustrate recent trend in sentiment analysis and its related works.Keywords
This publication has 20 references indexed in Scilit:
- Contextual semantics for sentiment analysis of TwitterInformation Processing & Management, 2016
- Subjectivity and sentiment analysis: An overview of the current state of the area and envisaged developmentsDecision Support Systems, 2012
- CROWDSOURCING A WORD–EMOTION ASSOCIATION LEXICONComputational Intelligence, 2012
- Polarity analysis of texts using discourse structure2011
- DASA: Dissatisfaction-oriented Advertising based on Sentiment AnalysisExpert Systems with Applications, 2010
- Using appraisal groups for sentiment analysis2005
- Recognizing contextual polarity in phrase-level sentiment analysis2005
- Mining the peanut gallery2003
- Support-vector networksMachine Learning, 1995
- Induction of decision treesMachine Learning, 1986