Is a Voting Approach Accurate for Opinion Mining?

Plantié, Michel; Roche, Mathieu; Dray, Gérard; Poncelet, Pascal

doi:10.1007/978-3-540-85836-2_39

Cited by 12 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There are many approaches followed for sentiment and opinion analysis including for data cleansing. Natural language processing, artificial intelligence including machine learning, statistical methods and web tools are major approaches to opinion mining [9,10]. Each of them has its own advantages and limitations.…”

Section: Approachesmentioning

confidence: 99%

Opinion Mining: A Survey

NandhaKumar¹,

Christopher²

2015

IJCA

View full text Add to dashboard Cite

Opining mining has gained high level focus in business and commercial fields. The opinions are considered as valuable data. Opinions are customer reviews, comments and feelings and collected from web forums, websites, and user groups which are posted by thousands of end users and also recorded manually. The collected opinions are processed by various techniques, algorithms, methods and software tools in order to extract the meaning from them. Extraction of meaningful information from opinions is given more importance in the field of business analytics. This entire process is popularly known as opinion mining or sentiment analysis and they are used in industries to develop quality of services, products. This article is an outcome of a study which made on various sub tasks, approaches, methods and techniques involved and applied in opinion mining.

show abstract

Section: Approachesmentioning

confidence: 99%

Opinion Mining: A Survey

NandhaKumar¹,

Christopher²

2015

IJCA

View full text Add to dashboard Cite

show abstract

“…Since the probability results obtained by individual classifiers are not commensurate, voting techniques based on the final results of each classifier are the most appropriate for combining very different classifier systems. Plantié, Roche, Dray, and Poncelet () applied different voting procedures to several OM corpora using three classifiers (SVM, Bayes Multinomial, and Radial Basis Function [RBF] network). The results were very encouraging and showed that the use of a voting approach outperforms the accuracy of the individual classifiers.…”

Section: Related Workmentioning

confidence: 99%

Improving polarity classification of bilingual parallel corpora combining machine learning and semantic orientation approaches

Perea‐Ortega

Martín–Valdivia

Ureña‐López

et al. 2013

J Am Soc Inf Sci Tec

View full text Add to dashboard Cite

Polarity classification is one of the main tasks related to the opinion mining and sentiment analysis fields. The aim of this task is to classify opinions as positive or negative. There are two main approaches to carrying out polarity classification: machine learning and semantic orientation based on the integration of knowledge resources. In this study, we propose to combine both approaches using a voting system based on the majority rule. In this way, we attempt to improve the polarity classification of two parallel corpora such as the opinion corpus for Arabic (OCA) and the English version of the OCA (EVOCA). Several experiments have been performed to check the feasibility of the proposed method. The results show that the experiment that took into account both approaches in the voting system obtained the best performance. Moreover, it is also shown that the proposed method slightly improves the best results obtained using machine learning approaches solely over the OCA and the EVOCA separately. Therefore, we can conclude that the approach proposed here might be considered a good strategy for polarity detection when we work with bilingual parallel corpora.

show abstract

“…The main assumption in [12] is that an opinion can be detected by the adjectives used. Two kind of methods exist to detect opinions: using a corpus of opinions done by experts [21] or using adjectives repositories such as WordNet [16] [14]. Results will largely differ depending on the corpus used.…”

Section: E-democracy and Online Debatesmentioning

confidence: 99%