Automatically assessing review helpfulness

Kim, Soo-Min; Pantel, Patrick; Chklovski, Tim; Pennacchiotti, Marco

doi:10.3115/1610075.1610135

Cited by 358 publications

(351 citation statements)

References 24 publications

Supporting

Mentioning

332

Contrasting

Unclassified

Order By: Relevance

“…reviewer history, reputation etc.). A similar approach was proposed in [27], where review ratings, length and unigram term distribution were found to be among the most discriminating features from a helpfulness perspective. Timeliness of reviews and reviewer expertise also proved to be useful predictors of movie review helpfulness [34], indicating that older reviews are less appreciated by consumers and that reviewers with an interest in and knowledge of particular movie genres are likely to author high quality reviews for similar-genre movies in the future.…”

Section: Related Workmentioning

confidence: 94%

“…In particular the opinions expressed in user-generated content can provide powerful insights in many different contexts and the opinion mining literature is replete with a variety of significant challenges, mature techniques and significant results. This includes work in sub-areas such as sentiment analysis [31,44,8,62,63,64], aspect-oriented opinion mining [24,4,50,21,22,66,11], opinion summarization [21,32,70,58,26,45], opin-ion search and retrieval [67,68,40,23], and product review helpfulness estimation [69,28,42,33,15] to name but a few.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Combining similarity and sentiment in opinion mining for product recommendation

et al. 2015

View full text Add to dashboard Cite

In the world of recommender systems, so-called content-based methods are an important approach that rely on the availability of detailed product or item descriptions to drive the recommendation process. For example, recommendations can be generated for a target user by selecting unseen products that are similar to the products that the target user has liked or purchased in the past. To do this, content-based methods must be able to compute the similarity between pairs of products (unseen products and liked products, for example) and typically this is achieved by comparing product features or other descriptive elements. The approach works well when product descriptions are readily available and when they are detailed enough to afford an effective similarity comparison. But this is not always the case. Detailed product descriptions may not be available since they can be expensive to create and maintain. In this article we consider another source of product descriptions in the form of the user-generated reviews that frequently accompany products on the web. We ask whether it is possible to mine these reviews, unstructured and noisy as they are, to produce useful product descriptions that can be used in a recommendation system. In particular we describe a novel approach to product recommendation that harnesses not only the features that can be mined from user-generated reviews but also the expressions of sentiment that are associated with these features. We present a recommendation ranking strategy that combines similarity and sentiment to suggest products that are similar but superior to a query product according to the opinion of reviewers, and we demonstrate the practical benefits of this approach across a variety of Amazon product domains.

show abstract

Section: Related Workmentioning

confidence: 94%

Section: Related Workmentioning

confidence: 99%

Combining similarity and sentiment in opinion mining for product recommendation

et al. 2015

View full text Add to dashboard Cite

show abstract

“…In [28], a semi-supervised learning method is applied, and in [46], the decision is made by simply summing up opinion words in a sentence. [47,48,49] build models to identify some specific types of opinions in reviews.…”

Section: Assumption Of Sentence-level Sentiment Classificationmentioning

confidence: 99%

“…A related problem that has also been studied in the past few years is the determination of the usefulness, helpfulness or utility of a review [31,49,57,110]. The idea is to determine how helpful a review is to a user.…”

Section: Opinion Spam and Utility Of Opinionsmentioning

confidence: 99%

“…Researchers have used many types of data features for model building [31,49,110]. Example features include review length, review ratings (the number of stars), counts of some specific POS tags, opinion words, tf-idf weighting scores, wh-words, product attribute mentions, product brands, comparison with product specifications, and comparison with editorial reviews, and many more.…”

Section: Utility Of Reviewsmentioning

confidence: 99%

See 1 more Smart Citation

The Customer is Always Right: Sentiment Analysis for Bank Service Quality

Brunova¹,

Bidulya²

2017

TSU Herald. Hum Res. Humanitates

View full text Add to dashboard Cite

Textual information in the world can be broadly categorized into two main types: facts and opinions. Facts are objective expressions about entities, events and their properties. Opinions are usually subjective expressions that describe people's sentiments, appraisals or feelings toward entities, events and their properties. The concept of opinion is very broad. In this chapter, we only focus on opinion expressions that convey people's positive or negative sentiments. Much of the existing research on textual information processing has been focused on mining and retrieval of factual information, e.g., information retrieval, Web search, text classification, text clustering and many other text mining and natural language processing tasks. Little work had been done on the processing of opinions until only recently. Yet, opinions are so important that whenever we need to make a decision we want to hear others' opinions. This is not only true for individuals but also true for organizations.One of the main reasons for the lack of study on opinions is the fact that there was little opinionated text available before the World Wide Web. Before the Web, when an individual needed to make a decision, he/she typically asked for opinions from friends and families. When an organization wanted to find the opinions or sentiments of the general public about its products and services, it conducted opinion polls, surveys, and focus groups. However, with the Web, especially with the explosive growth of the usergenerated content on the Web in the past few years, the world has been transformed.The Web has dramatically changed the way that people express their views and opinions. They can now post reviews of products at merchant sites and express their views on almost anything in Internet forums, discussion groups, and blogs, which are collectively called the user-generated content. This online wordof-mouth behavior represents new and measurable sources of information with many practical applications. Now if one wants to buy a product, he/she is no longer limited to asking his/her friends and families because there are many product reviews on the Web which give opinions of existing users of the product. For a company, it may no longer be necessary to conduct surveys, organize focus groups or employ external consultants in order to find consumer opinions about its products and those of its competitors because the user-generated content on the Web can already give them such information.However, finding opinion sources and monitoring them on the Web can still be a formidable task because there are a large number of diverse sources, and each source may also have a huge volume of opinionated text (text with opinions or sentiments). In many cases, opinions are hidden in long forum posts and blogs. It is difficult for a human reader to find relevant sources, extract related sentences with opinions, read them, summarize them, and organize them into usable forms. Thus, automated opinion discovery and summarization systems are needed. Sentiment an...

show abstract

Predicting podcast preference: An analysis framework and its application

Tsagkias

Larson

Rijke

2009

J. Am. Soc. Inf. Sci.

View full text Add to dashboard Cite

Finding worthwhile podcasts can be difficult for listeners since podcasts are published in large numbers and vary widely with respect to quality and repute. Independently of their informational content, certain podcasts provide satisfying listening material while other podcasts have little or no appeal. In this paper we present PodCred, a framework for analyzing listener appeal, and we demonstrate its application to the task of automatically predicting the listening preferences of users. First, we describe the PodCred framework, which consists of an inventory of factors contributing to user perceptions of the credibility and quality of podcasts. The framework is designed to support automatic prediction of whether or not a particular podcast will enjoy listener preference. It consists of four categories of indicators related to the Podcast Content, the Podcaster, the Podcast Context, and the Technical Execution of the podcast. Three studies contributed to the development of the PodCred framework: a review of the literature on credibility for other media, a survey of prescriptive guidelines for podcasting, and a detailed data analysis. Next, we report on a validation exercise in which the PodCred framework is applied to a real-world podcast preference prediction task. Our validation focuses on select framework indicators that show promise of being both discriminative and readily accessible. We translate these indicators into a set of easily extractable "surface" features and use them to implement a basic classification system. The experiments carried out to evaluate system use popularity levels in iTunes as ground truth and demonstrate that simple surface features derived from the PodCred framework are indeed useful for classifying podcasts. IntroductionPodcasts are audio series published online. As new episodes of a podcast are created, they are added to the podcast feed and are distributed over the Internet (Patterson, 2006;van Gils, 2008). Users either download episodes individually for listening or subscribe to the feed of a podcast, so that new episodes are automatically downloaded as they are published. Not every podcast is an equally valuable source of information and entertainment. Finding worthwhile podcasts among the large volumes of podcasts available online, which vary widely in quality and repute, can be a daunting task for podcast listeners and subscribers. We present an analysis framework, called PodCred, for assessing the credibility and quality on podcasts on the Internet. The framework is designed to support prediction of whether a listener will select one podcast over another, given that both podcasts contain comparable informational content. We demonstrate the utility of the framework with a validation exercise that demonstrates its ability to support prediction of listener appeal, i.e., the potential of a podcast to enjoy favor and preference among users. 1 Podcasts are compared to radio programs by some definitions (Heffernan, 2005;Matthews, 2006). However, podcasting on the Internet and ra...

show abstract

Automatically assessing review helpfulness

Cited by 358 publications

References 24 publications

Combining similarity and sentiment in opinion mining for product recommendation

Combining similarity and sentiment in opinion mining for product recommendation

The Customer is Always Right: Sentiment Analysis for Bank Service Quality

Predicting podcast preference: An analysis framework and its application

Contact Info

Product

Resources

About