Using supervised learning to classify authentic and fake online reviews

Banerjee, Snehasish; Chua, Alton Y. K.; Kim, Jung‐Jae

doi:10.1145/2701126.2701130

Cited by 55 publications

(30 citation statements)

References 28 publications

(84 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, the detection of fake reviews based only on textual features is challenging. Other articles propose additional textual features such as semantic similarity and emotion [37], a wide variety of lexical and syntactic features [14] and deeper details such as understandability, level of details, writing style and cognition indicators [3].…”

Section: Related Workmentioning

confidence: 99%

A framework for fake review detection in online consumer electronics retailers

Barbado

Araque

Iglesias

2019

Information Processing & Management

198

View full text Add to dashboard Cite

The impact of online reviews on businesses has grown significantly during last years, being crucial to determine business success in a wide array of sectors, ranging from restaurants, hotels to e-commerce. Unfortunately, some users use unethical means to improve their online reputation by writing fake reviews of their businesses or competitors. Previous research has addressed fake review detection in a number of domains, such as product or business reviews in restaurants and hotels. However, in spite of its economical interest, the domain of consumer electronics businesses has not yet been thoroughly studied. This article proposes a feature framework for detecting fake reviews that has been evaluated in the consumer electronics domain. The contributions are fourfold: (i) construction of a dataset for classifying fake reviews in the consumer electronics domain in four different cities based on scraping techniques; (ii) definition of a feature framework for fake review detection; (iii) development of a fake review classification method based on the proposed framework and (iv) evaluation and analysis of the results for each of the cities under study. We have reached an 82% F-Score on the classification task and the Ada Boost classifier has been proven to be the best one by statistical means according to the Friedman test.

show abstract

Section: Related Workmentioning

confidence: 99%

A framework for fake review detection in online consumer electronics retailers

Barbado

Araque

Iglesias

2019

Information Processing & Management

198

View full text Add to dashboard Cite

show abstract

“…The time horizon analyzed was from 10-17 June 2019, allowing the download of a total of n = 10,786 tweets under the search term #Education. Following Sherman et al [39] and Banerjee et al [40], we used a randomized controlled process to select this term by focusing on the education sector and the proposed research questions. This process allows researchers to systematically select a sample based on the social media content-in this study, in the form of tweets with a specific hashtag.…”

Section: Data Sampling Extraction and Collectionmentioning

confidence: 99%

How to Extract Meaningful Insights from UGC: A Knowledge-Based Method Applied to Education

2019

View full text Add to dashboard Cite

New analysis and visualization techniques are required to glean useful insights from the vast amounts of data generated by new technologies and data sharing platforms. The aim of this article is to lay a foundation for such techniques so that the age of big data may also be the age of knowledge, visualization, and understanding. Education is the keystone area used in this study because it is deeply affected by digital platforms as an educational medium and also because it deals mostly with digital natives who use information and communication technology (ICT) for all manner of purposes. Students and teachers are therefore a rich source of user generated content (UGC) on social networks and digital platforms. This article shows how useful knowledge can be extracted and visualized from samples of readily available UGC, in this case the text published in tweets from the social network Twitter. The first stage employs topic-modeling using LDA (latent dirichlet allocation) to identify topics, which are then subjected to sentiment analysis (SA) using machine-learning (developed in Python). The results take on meaning through an application of data mining techniques and a data visualization algorithm for complex networks. The results obtained show insights related to innovative educational trends that practitioners can use to improve strategies and interventions in the education sector in a short-term future.

show abstract

“…Specifically, after connecting to the public Twitter API to collect the data, we downloaded a total of 21,061 tweets that contained the hashtag #DigitalMarketing. Following Sherman et al [43] and Banerjee et al [44], we used a randomized controlled process to select this search term.…”

Section: Data Samplingmentioning

confidence: 99%

Comparing Data-Driven Methods for Extracting Knowledge from User Generated Content

Saura

Reyes-Menéndez

Filipe

2019

Journal of Open Innovation: Technology, Market, and Complexity

View full text Add to dashboard Cite

This study aimed to compare two techniques of business knowledge extraction for the identification of insights related to the improvement of digital marketing strategies on a sample of 15,731 tweets. The sample was extracted from user generated content (UGC) from Twitter using two methods based on knowledge extraction techniques for business. In Method 1, an algorithm to detect communities in complex networks was applied; this algorithm, in which we applied data visualization techniques for complex networks analysis, used the modularity of nodes to discover topics. In Method 2, a three-phase process was developed for knowledge extraction that included the application of a latent Dirichlet allocation (LDA) model, a sentiment analysis (SA) that works with machine learning, and a data text mining (DTM) analysis technique. Finally, we compared the results of each of the two techniques to see whether or not the results yielded by these two methods regarding the analysis of companies’ digital marketing strategies were mutually complementary.

show abstract

Using supervised learning to classify authentic and fake online reviews

Cited by 55 publications

References 28 publications

A framework for fake review detection in online consumer electronics retailers

A framework for fake review detection in online consumer electronics retailers

How to Extract Meaningful Insights from UGC: A Knowledge-Based Method Applied to Education

Comparing Data-Driven Methods for Extracting Knowledge from User Generated Content

Contact Info

Product

Resources

About