Exploring determinants of voting for the “helpfulness” of online user reviews: A text mining approach

Cao, Qing; Duan, Wenjing; Gan, Qiwei

doi:10.1016/j.dss.2010.11.009

Cited by 536 publications

(411 citation statements)

References 22 publications

Supporting

Mentioning

336

Contrasting

Unclassified

Order By: Relevance

“…These mixed findings might stem from (1) methodological shortcomings, such as a cross-sectional context and inability to control for unobserved differences, including product quality (Zhu and Zhang 2010), or (2) the inability of numeric cues to do justice to the nuanced, fine-grained, and expressive nature of verbatim reviews (Cao, Duan, and Gan 2011;Pavlou and Dimoka 2006;Singh, Hillmer, and Ze 2011). Making use of recent advances in text analytics to systematically analyze large volumes of collections of customer review verbatim scripts and taking a dynamic perspective, which is more reflective of the rapid, continual changes in user-generated content (Tirunillai and Tellis 2012), may clarify the impacts of review content on conversion rates (Chevalier and Mayzlin 2006;Mudambi and Schuff 2010).…”

Section: Conceptual Foundationsmentioning

confidence: 99%

“…We aggregated all review scores for the same product to derive a mean level for each week, that is, an intensity percentage or summary score between -1 and 1, depending on relative intensity of negative or positive affective content across all reviews for that product in a given week. Because review titles are particularly prominent, we mined and conducted separate calculations for title and text intensities similar to Cao, Duan, and Gan (2011). The aggregation is as follows:…”

Section: Measurement Developmentmentioning

confidence: 99%

“…Online retailers thus recognize the effectiveness of customer reviews for converting customer visits into sales; Roku, the market leader in innovative applications for digital media, attributes a 20% lift in its online conversion rates to the appearance of approximately 17,000 (both positive and negative) customer reviews on its website (Bronto.com 2011). Yet the sheer volume and lack of structure of qualitative information in customer reviews continues to present a formidable challenge (Cao, Duan, and Gan 2011;Singh, Hillmer, and Ze 2011). Most online retailers believe their performance is hampered because they cannot efficiently decipher or reliably assess how online customers use the informational cues from their online conversations at a manageable, product category level (Bonnet and Nandan 2011).…”

mentioning

confidence: 99%

See 2 more Smart Citations

More than Words: The Influence of Affective Content and Linguistic Style Matches in Online Reviews on Conversion Rates

Ludwig

Ruyter

Friedman

et al. 2013

Journal of Marketing

578

435

View full text Add to dashboard Cite

Citation: Ludwig, S., de Ruyter, K., Friedman, M., Brüggen, E., Wetzels, M. & Pfann, G. (2013). More than words: The influence of affective content and linguistic style matches in online reviews on conversion rates. Journal of Marketing, 77(1), pp. 87-103. doi: 10.1509/jm.11.0560 This is the published version of the paper.This version of the publication may differ from the final published version. Customers increasingly rely on other consumers' reviews to make purchase decisions online. New insights into the customer review phenomenon can be derived from studying the semantic content and style properties of verbatim customer reviews to examine their influence on online retail sites' conversion rates. The authors employ text mining to extract changes in affective content and linguistic style properties of customer book reviews on Amazon.com. A dynamic panel data model reveals that the influence of positive affective content on conversion rates is asymmetrical, such that greater increases in positive affective content in customer reviews have a smaller effect on subsequent increases in conversion rate. No such tapering-off effect occurs for changes in negative affective content in reviews. Furthermore, positive changes in affective cues and increasing congruence with the product interest group's typical linguistic style directly and conjointly increase conversion rates. These findings suggest that managers should identify and promote the most influential reviews in a given product category, provide instructions to stimulate reviewers to write powerful reviews, and adapt the style of their own editorial reviews to the relevant product category. Permanent

show abstract

Section: Conceptual Foundationsmentioning

confidence: 99%

Section: Measurement Developmentmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

More than Words: The Influence of Affective Content and Linguistic Style Matches in Online Reviews on Conversion Rates

Ludwig

Ruyter

Friedman

et al. 2013

Journal of Marketing

578

435

View full text Add to dashboard Cite

show abstract

“…This may seem like weak measure of quality, but the history of automatic quality assessment is saturated with findings that length is the best predictor of quality. This holds true for both answers to questions Surdeanu et al, 2011;Beygelzimer et al, 2015); as well as e-commerce reviews (Cao et al, 2011;Racherla and Friske, 2012). Of course, length is not as shallow as it may seem at first; given no strong incentive for authors to leave long comments, length is likely a proxy for thoroughness of the comment.…”

Section: Discussionmentioning

confidence: 99%

Assessing Objective Recommendation Quality through Political Forecasting

Schwartz

Rouhizadeh

Bishop

et al. 2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Recommendations are often rated for their subjective quality, but few researchers have studied quality in terms of objective utility. We explore quality assessment with respect to both subjective (i.e. users' ratings) and objective (i.e., did it influence? did it improve decisions?) metrics in a massive online geopolitical forecasting system, ultimately comparing linguistic characteristics of each quality metric. Using a variety of features, we predict all types of quality with better accuracy than the simple yet strong baseline of recommendation length. For example, more complex sentence constructions, as evidenced by subordinate conjunctions, are characteristic of recommendations leading to objective improvements in forecasting. Our analyses also reveal rater biases; for example, forecasters are subjectively biased in favor of recommendations mentioning business deals and material things, even though such recommendations do not indeed prove any more useful objectively.

show abstract

“…Understandability was performed as surface-level characteristics. Structural features were calculated as the number of characters per word, number of words, and fraction of words containing 7 or more characters is called long word [4].…”

Section: Proposed Systemmentioning

confidence: 99%

Anomaly Detection based on Review Burstness and Ranking Fraud Discovery

Alexander¹,

Rahila²,

Shameem³

2017

IJCA

View full text Add to dashboard Cite

Nowadays everyone is using smart phone. Many applications are in smart phone. To download an application user visit App store such as Google play store, Apple play store etc, then he or she is able to see the different application lists. User has no awareness about the application. So user looks at the list and download the application from App Store based on the mobile app rank. App developers use different ways to promote their Apps in order to get top position in App store for example, high rating and good reviews are given about the mobile app i.e. there is fraud behavior occur it. To detect fraud behavior first identify the active periods of mobile app, namely leading session of mobile apps. In the existing system the leading event and leading session of an app identified from the collected historical records. Then ranking based evidence, rating based evidence and review based evidence were collected from the historical records. These evidence score value is used to detect fraud behavior occur in the mobile app. In proposed system from the reviews of mobile app it identifies if it is a fake review or not.

show abstract

Exploring determinants of voting for the “helpfulness” of online user reviews: A text mining approach

Cited by 536 publications

References 22 publications

More than Words: The Influence of Affective Content and Linguistic Style Matches in Online Reviews on Conversion Rates

More than Words: The Influence of Affective Content and Linguistic Style Matches in Online Reviews on Conversion Rates

Assessing Objective Recommendation Quality through Political Forecasting

Anomaly Detection based on Review Burstness and Ranking Fraud Discovery

Contact Info

Product

Resources

About