A Joint Model of Feature Mining and Sentiment Analysis for Product Review Rating

Carrillo-de-Albornoz, Jorge; Plaza, Laura; Gervás, Pablo; Díaz, Alberto

doi:10.1007/978-3-642-20161-5_8

Cited by 61 publications

(40 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The information gleaned from customer reviews is of great interest to both companies and consumers because it is usually presented in the form of unstructured free text. As such, automatically extracting and rating user opinions about a product is a challenging task (de Albornoz, Plaza, Gervás, & Díaz, 2011). The electronic distribution of room information, prices, and availability has changed the channels that people use to reserve hotel rooms, from travel agents and hotel chains' call centres to using online booking platforms (Carroll & Siguaw, 2003;Tso & Law, 2005).…”

Section: Research Scope and Methodsmentioning

confidence: 99%

Growth of a platform business model as an entrepreneurial ecosystem and its effects on regional development

Yun

Won

Park

et al. 2017

European Planning Studies

View full text Add to dashboard Cite

show abstract

Section: Research Scope and Methodsmentioning

confidence: 99%

Growth of a platform business model as an entrepreneurial ecosystem and its effects on regional development

Yun

Won

Park

et al. 2017

European Planning Studies

View full text Add to dashboard Cite

show abstract

“…Yacouel and Fleischer (2012) found that, holding everything else constant, high rating scores are associated with higher prices for the hotel sector in an important e-commerce platform, Booking.com. Similarly, de Albornoz et al (2011) reported that user-generated ratings have a significant impact on purchasing decisions, so that consumers are willing to pay about 20% more for services receiving the highest score than for similar services receiving a slightly lower score.…”

Section: The Impact Of Rating Systemsmentioning

confidence: 99%

Social Influence Bias in Online Ratings: A Field Experiment

2016

View full text Add to dashboard Cite

The aim of this paper is to study the empirical phenomenon of rating bubbles, i.e. clustering on extremely positive values in e-commerce platforms and rating web sites. By means of a field experiment that exogenously manipulates prior ratings for a hotel in an important Italian tourism destination, we investigate whether consumers are influenced by prior ratings when evaluating their stay (i.e., social influence bias). Results show that positive social influence exists, and that herd behavior is asymmetric: information on prior positive ratings has a stronger influence on consumers' rating attitude than information on prior mediocre ratings. Furthermore, we are able to exclude any brag-or-moan effect: the behavior of frequent reviewers, on average, is not statistically different from the behavior of consumers who have never posted ratings online. Yet, non-reviewers exhibit a higher influence to excellent prior ratings, thus lending support to the social influence bias interpretation. Finally, also repeat customers are affected by prior ratings, although to a lesser extent with respect to new customers.

show abstract

“…As for more retrieval-oriented tasks, the ranking of products and reviews benefits from sentiment detection [10]: by identifying categories important to the users from sentiments expressed on Twitter, products ca be re-ranked accordingly. Moreover cross-language retrieval and ranking can incorporate sentiments and their respective translations [19].…”

Section: Related Workmentioning

confidence: 99%

Twitter Sentiment Detection via Ensemble Classification Using Averaged Confidence Scores

Hagen

Potthast

Büchner

et al. 2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We reproduce three classification approaches with diverse feature sets for the task of classifying the sentiment expressed in a given tweet as either positive, neutral, or negative. The reproduced approaches are also combined in an ensemble, averaging the individual classifiers' confidence scores for the three classes and deciding sentiment polarity based on these averages. Our experimental evaluation on SemEval data shows our re-implementations to slightly outperform their respective originals. Moreover, in the SemEval Twitter sentiment detection tasks of 2013 and 2014, the ensemble of reproduced approaches would have been ranked in the top-5 among 50 participants. An error analysis shows that the ensemble classifier makes few severe misclassifications, such as identifying a positive sentiment in a negative tweet or vice versa. Instead, it tends to misclassify tweets as neutral that are not, which can be viewed as the safest option.

show abstract

A Joint Model of Feature Mining and Sentiment Analysis for Product Review Rating

Cited by 61 publications

References 11 publications

Growth of a platform business model as an entrepreneurial ecosystem and its effects on regional development

Growth of a platform business model as an entrepreneurial ecosystem and its effects on regional development

Social Influence Bias in Online Ratings: A Field Experiment

Twitter Sentiment Detection via Ensemble Classification Using Averaged Confidence Scores

Contact Info

Product

Resources

About