Can online product reviews be more helpful? Examining characteristics of information content by product type

Weathers, Danny; Swain, Scott D.; Grover, Varun

doi:10.1016/j.dss.2015.07.009

Cited by 141 publications

(68 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some of the linguistic features were marked as effective for predicting review helpfulness. Weathers et al (2015) focused on the diagnosticity and credibility of electronic wordof-mouth. Diagnosticity explains the uncertainty and equivocality of the reviewer, whereas credibility defines the trust and expertise of the reviewer.…”

Section: Automated Approach For Helpfulness Predictionmentioning

confidence: 99%

Ranking online consumer reviews

Saumya

Singh

Baabdullah

et al. 2018

Electronic Commerce Research and Applications

View full text Add to dashboard Cite

The product reviews are posted online in the hundreds and even in the thousands for some popular products.Handling such a large volume of continuously generated online content is a challenging task for buyers, sellers and even researchers. The purpose of this study is to rank the overwhelming number of reviews using their predicted helpfulness score. The helpfulness score is predicted using features extracted from review text data, product description data and customer question-answer data of a product using randomforest classifier and gradient boosting regressor. The system is made to classify the reviews into low or high quality by random-forest classifier. The helpfulness score of the high quality reviews is only predicted using gradient boosting regressor. The helpfulness score of the low quality reviews is not calculated because they are never going to be in the top k reviews. They are just added at the end of the review list to the reviewlisting website. The proposed system provides fair review placement on review listing pages and making all high quality reviews visible to customers on the top. The experimental results on data from two popular 1 Sunils.cse15@nitp.ac.in 2 jps@nitp.ac.in 3 baabdullah@kau.edu.sa 4 nrananp@gmail.com 5Indian e-commerce websites validate our claim, as 3-4 new high-quality reviews are placed in the top ten reviews along with 5-6 old reviews based on review helpfulness. Our findings indicate that inclusion of features from product description data and customer question-answer data improves the prediction accuracy of the helpfulness score. positive reviews 7 , all negative reviews 8 , or reviews with star ratings. However, the sorting algorithm for top reviews used by Amazon is not public.People prefer to read helpful reviews over recent reviews because helpful reviews indicate sufficient acceptance by similar users, which helps establish trust in the review. The helpfulness of online reviews is achieved by asking a simple question: "was this review helpful to you?" Users are asked to give their opinion by clicking either "thumbs up" or "thumbs down" buttons. However, due to a large number of reviews available for each product, helpfulness voting does not solve all problems. In fact, the listing of reviews based on helpfulness votes suffers from the Matthew effect (Merton, 1968), which states that a review that is at the top of the review list will remain on top because users mostly access and vote for a few of the top reviews before making their purchase decisions, whereas a review that is at the bottom of the review list will remain at the bottom because users hardly notice them (Singh et al., 2017a). A new review that has just appeared on the product page and has not received significant votes until recently may remain at the bottom of the review list. It may be the case that the review has the potential to rise to the top of the review list. This may negatively affect the relationship between reviewer and website. The reviewer may become demotivated and may not write reviews fo...

show abstract

Section: Automated Approach For Helpfulness Predictionmentioning

confidence: 99%

Ranking online consumer reviews

Saumya

Singh

Baabdullah

et al. 2018

Electronic Commerce Research and Applications

View full text Add to dashboard Cite

show abstract

“…In this study, text-related and source-related variables, whose effect on helpfulness of reviews has been established in past literature, were controlled. These variables included the review rating (Baek et al, 2012), reviewer identity (Forman et al, 2008), and the nature of the product (i.e., search or experience product; Mudambi & Schuff, 2010;Weathers, Swain, & Grover, 2015). Review rating was captured as the number of stars given in a particular review.…”

Section: Control Variablesmentioning

confidence: 99%

Online Review Helpfulness: Role of Qualitative Factors

Agnihotri

Bhattacharya

2016

Psychology and Marketing

119

View full text Add to dashboard Cite

Consumers are increasingly reading online reviews before making any purchasing decisions. The significance of online reviews has only grown over the years. Though in the past, scholars have emphasized the impact of quantitative factors (e.g., review ratings) on online reviews, only recently have they begun to explore the role of qualitative aspects of online reviews. Content readability and associated sentiments in text provide two important qualitative cues that influence the helpfulness of online reviews. However, the extant literature has overemphasized the linear association between these aspects and the helpfulness of reviews. Using the elaboration likelihood model and the classic ideal point concept, the current work asserts that after an ideal point is attained, lucid and sentimental reviews diminish in utility (i.e., helpfulness of an online review for consumers decreases). This may happen because consumers are wary of fraudulent reviews. This study proposes that if experienced reviewers give such extreme reviews, then consumers might still draw utility from these reviews. In other words, this study explains the moderating role of reviewer experience, which heuristically influences consumers’ trust of online reviews, thus making even too simplistic or extremely sentimental reviews helpful.

show abstract

“…A handful of studies (Ahmad & Laroche, 2015;Kim & Gupta, 2012;Yin et al, 2014) have examined the impact of emotions expressed in review content on perceived helpfulness of online reviews. Overall star rating, rating inconsistency Baek et al, 2012;Hu & Chen, 2016;Mudambi & Schuff, 2010;Robinson et al, 2012;Yan et al, 2016;Yin et al, 2016 Content Length, proportion of negative words, images/photos, valence, objectivity/subjectivity, emotions, emotion intensity, detailed information, explained actions and reactions, review format, review type (attributed value and simple recommendation), review Ahmad & Laroche, 2015;Baek et al, 2012;Cheng & Ho, 2015;Felbermayr & Nanopoulos, 2016;Folse et al, 2016;Hussain, et al 2017;Jeong & Koo, 2015;Karimi & Wang, 2017;Kaushik et al, 2018;Kim & Gupta, 2012;Li & Zhan, 2011;Lockie et al, 2015;Moore, 2015;Mudambi & Schuff, 2010;Ngo- Ye & diagnosticity, technical information, argument diversity, expertise claim, persuasive words, presentation mode Sinha, 2014; Park & Lee, 2008;Peng et al, 2014;Purnawirawan et al, 2015;Quaschning et al, 2015;Robinson et al, 2012;Teng et al, 2014;Weathers et al, 2015;Willemsen et al, 2011;Wu, 2013;…”

Section: Literature Reviewmentioning

confidence: 99%

Perceived helpfulness of eWOM: Emotions, fairness and rationality

Ismagilova

Dwivedi

Slade

2020

Journal of Retailing and Consumer Services

102

View full text Add to dashboard Cite

Consumers use online reviews to help make informed purchase decisions. This paper extends existing research by examining how content of online reviews influences perceptions of helpfulness by demonstrating how different emotions can influence helpfulness of both product and service online reviews beyond a valence-based approach using cognitive appraisal theory and attribution theory. This research contributes to existing knowledge regarding the theory of information processing, attribution theory, and cognitive appraisal theory of emotions. Using findings from this study, practitioners can make review websites more user-friendly which will help readers avoid information overload and make more informed purchase decisions.

show abstract

Can online product reviews be more helpful? Examining characteristics of information content by product type

Cited by 141 publications

References 87 publications

Ranking online consumer reviews

Ranking online consumer reviews

Online Review Helpfulness: Role of Qualitative Factors

Perceived helpfulness of eWOM: Emotions, fairness and rationality

Contact Info

Product

Resources

About