Sentiment analysis: A review and comparative analysis of web services

Serrano-Guerrero, Jesús; Olivas, José Á.; Romero, Francisco P.; Herrera‐Viedma, Enrique

doi:10.1016/j.ins.2015.03.040

Cited by 371 publications

(175 citation statements)

References 85 publications

Supporting

Mentioning

166

Contrasting

Unclassified

Order By: Relevance

“…Liu and Zhang [30], Serrano-Guerrero et al [42], Nassirtoussi et al [35], and Cambria et al [3] provides state-of-art survey on sentiment analysis/opinion mining and text mining for market prediction. Paper [27] proposed a framework for measurement of customer satisfaction for mobile services by combining a ranking method and sentiment analysis.…”

Section: Review Analysis and Miningmentioning

confidence: 99%

Reputation Systems: Evaluating Reputation Among All Good Sellers

Jha

Ramu

Shenoy

et al. 2017

Data-Enabled Discov. Appl.

View full text Add to dashboard Cite

A reputation system assists people selecting whom to trust, encourages trustworthy action, and discourages participation of unskilled or dishonest. The "all good reputation" problem is common in current reputation systems, especially in e-commerce domain, making it difficult for buyers to choose credible sellers. Observing high growth of online data in Hindi language, in this paper, we propose a reputation system in this language. The functions of this system include (1) review mining for different criteria of online transactions, (2) calculation of reputation rating using Bayesian method, (3) calculation of reputation weight using typed dependency relation representation and Latent Dirichlet Allocation topic modeling technique for each criteria from user reviews, and (4) ranking sellers based on computed reputation score. Extensive simulations conducted on eBay dataset and TripAdvisor dataset show its effectiveness in solving "all good reputation" problem. So far, as our knowledge is concerned, this is the first work in Hindi language on reputation system. Keywords E-commerce · Hindi · Natural language processing · Reputation system · Review mining Highlights -The proposed Reputation System is a solution to "all good reputation" problem in e-commerce domain.Vandana Jha vjvandanajha@gmail.com 1 Department of Computer Science and Engineering, University Visvesvaraya College of Engineering, Bangalore University, Bangalore, India -Our system is implemented on Hindi language Product reviews and Hotel reviews. It can be easily extended to any reviews in e-commerce domain by using language specific parser and tagger. -Several experiments have been performed and the results obtained are more accurate in ranking the sellers. -Our system is compared with existing system for ranking the sellers. The sellers which were at the same rank using existing system, can be accurately ranked at different levels using our approach.

show abstract

Section: Review Analysis and Miningmentioning

confidence: 99%

Reputation Systems: Evaluating Reputation Among All Good Sellers

Jha

Ramu

Shenoy

et al. 2017

Data-Enabled Discov. Appl.

View full text Add to dashboard Cite

show abstract

“…1 Sentiment Analysis, Opinion Mining, and Subjectivity Analysis are broadly used as synonyms, although some sources make a difference between the concepts (Pang & Lee 2008;Serrano-Guerrero et al 2015). 6 Free and open corpus of paragraphs http://peeter.eki.ee:5000/valence/paragraphsquery/.…”

Section: Identifying Polarity In Different Text Typesmentioning

confidence: 99%

Identifying Polarity in Different Text Types

Pajupuu¹,

Altrov²,

Pajupuu³

2016

FEJF

View full text Add to dashboard Cite

While Sentiment Analysis aims to identify the writer's attitude toward individuals, events or topics, our aim is to predict the possible effect of a written text on the reader. For this purpose, we created an automatic identifier of the polarity of Estonian texts, which is independent of domain and of text type. Depending on the approach chosen -lexicon-based or machine learning -the identifier uses either a lexicon of words with a positive or negative connotation, or a text corpus where orthographic paragraphs have been annotated as positive, negative, neutral or mixed. Both approaches worked well, resulting in a nearly 75% accuracy on average. It was found that in some cases the results depend on the text type, notably, with sports texts the lexicon-based approach yielded a maximum accuracy of 80.3%, while over 88% was gained for opinion stories approached by machine learning.

show abstract

“…Sentiment Analysis, also called Opinion Mining, is currently one of the most studied research fields which aims to analyse people's opinions and emotions on products, individuals, organizations, and services [11]. The task of providing numerical ratings to textual reviews using a multi-point rating scale is referred to as rating-inference, belonging to the research area of Opinion Mining.…”

Section: Literature Reviewmentioning

confidence: 99%

A computational intelligence approach to efficiently predicting review ratings in e-commerce

Cosma

2016

Applied Soft Computing

View full text Add to dashboard Cite

Sentiment Analysis, also called Opinion Mining, is currently one of the most studied research fields which aims to analyse people's opinions. Ecommerce websites allow users to share opinions about a product/service by providing textual reviews along with numerical ratings. These opinions greatly influence future consumer purchasing decisions. This paper introduces an innovative computational intelligence framework for efficiently predicting customer review ratings by addressing two important issues involved in this significant task: the dimension and imprecision of customer textual review data. In particular, the proposed framework integrates the techniques of Singular Value Decomposition (SVD) and dimensionality reduction, Fuzzy C-Means (FCM) and the Adaptive Neuro-Fuzzy Inference System (ANFIS). The performance of the proposed approach returned high accuracy and the results revealed that when large datasets are concerned, only a fraction of the data is needed for creating a system to predict the review ratings of textual reviews. Results from the experiments suggest that the proposed synergetic approach yields better prediction performance than other stateof-the-art rating predictors which are based on the conventional Artificial Neural Network, Fuzzy C-Means, and Support Vector Machine approaches. In addition, the proposed framework can be utilised for other classification and prediction tasks, and its neuro-fuzzy predictor module can be replaced by other classifiers.

show abstract

Sentiment analysis: A review and comparative analysis of web services

Cited by 371 publications

References 85 publications

Reputation Systems: Evaluating Reputation Among All Good Sellers

Reputation Systems: Evaluating Reputation Among All Good Sellers

Identifying Polarity in Different Text Types

A computational intelligence approach to efficiently predicting review ratings in e-commerce

Contact Info

Product

Resources

About