Review Spam Detection Using Opinion Mining

Narayan, Rohit; Rout, Jitendra Kumar; Jena, Sanjay Kumar

doi:10.1007/978-981-10-3376-6_30

Cited by 19 publications

(17 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Narayan et al () used different types of text related properties such as LIWC, Uni‐gram, and the sentiment score of each review and reached an accuracy of 86.25%, a precision of 90.00% and a recall of 83.72%. Etaiwi and Awajan () examined two text related properties: bag of words and words count and reached an accuracy of 87.31%, a precision of 52.78% and a recall of 92.63%.…”

Section: Evaluation Results and Discussionmentioning

confidence: 99%

“…• Spam reviews are detected using some review and reviewer-centric features. Narayan et al (2018) • Spam reviews are detected using some text related properties such as LIWC, POS, N-gram, and sentiment score of each review. Mani et al (2018) • Spam reviews are detected using some text related properties such as Uni-gram and Bi-gram properties.…”

Section: Fontanarava Et Al (2017)mentioning

confidence: 99%

“…Some of the aforementioned studies have proposed a spam reviews detection technique while working on the dataset "DOSC" such as Narayan et al (2018), Etaiwi and Awajan (2017), Mani et al (2018) and Etaiwi and Naymat (2017) while Vanta and Aono (2019) proposed the technique while working on "YelpNYC" dataset and (Fontanarava et al, 2017) worked on "YelpZIP" dataset. Narayan et al (2018) used different types of text related properties such as LIWC, Uni-gram, and the sentiment score of each review and reached an accuracy of 86.25%, a precision of 90.00% and a recall of 83.72%. Etaiwi and Awajan (2017) examined two text related properties: bag of words and words count and reached an accuracy of 87.31%, a precision of 52.78% and a recall of 92.63%.…”

Section: B) State-of-the-art Techniques Comparisonmentioning

confidence: 99%

See 2 more Smart Citations

An enhanced feature‐based sentiment analysis approach

Saeed

Helal

Badr

et al. 2019

WIREs Data Min & Knowl

View full text Add to dashboard Cite

In the last few years, online reviews where individuals express their thoughts, interests, experiences, and opinions have broadly spread over the internet. Sentiment analysis has evolved to analyze these online reviews and provide valuable insights for both individuals and organizations that may help them in making decisions. Unfortunately the performance of sentiment analysis process is affected by the nature of online reviews' content that may contain emoticons and negation words. Moreover, spam reviews have been written for the purpose of deceiving others. Therefore, there is a need to develop an approach that considers these issues. In this paper, an enhanced approach for sentiment analysis is proposed which aims to enhance the performance of classifying reviews based on their features and assigning accurate sentiment score to features. This enhanced approach is achieved by handling negation, detecting emoticons, and detecting spam reviews using a combination of different types of properties which leads to achieving better predictive performance. The proposed approach has been verified against three datasets of different sizes. The results indicate that the proposed approach achieves a maximum accuracy of about 99.06% in detecting spam reviews and a maximum accuracy of about 97.13% in classifying reviews. This article is categorized under: Algorithmic Development > Text Mining Technologies > Classification Technologies > Machine Learning

show abstract

Section: Evaluation Results and Discussionmentioning

confidence: 99%

Section: Fontanarava Et Al (2017)mentioning

confidence: 99%

Section: B) State-of-the-art Techniques Comparisonmentioning

confidence: 99%

See 1 more Smart Citation

An enhanced feature‐based sentiment analysis approach

Saeed

Helal

Badr

et al. 2019

WIREs Data Min & Knowl

View full text Add to dashboard Cite

show abstract

“…O trabalho proposto por Narayan et al [2018] consistiu na utilização de técnicas de Aprendizado de Máquina para reavaliar reviews fraudulentas sobre produtos. O LIWC foi utilizado em conjunto com n-gram feature para a classificação do conteúdo.…”

Section: Trabalhos Relacionadosunclassified

Mineração de Opiniões com LIWC: abordagem prática sobre sistemas judiciais eletrônicos brasileiros

Nascimento¹,

Nascimento²,

Carvalho³

et al. 2020

Anais Do Brazilian Workshop on Social Network Analysis and Mining (BraSNAM 2020)

View full text Add to dashboard Cite

A Mineração de Opinião engloba o estudo computacional de opiniões ou avaliações que as pessoas expressam em relação a entidades, produtos e serviços. O objetivo deste trabalho é avaliar e comparar opiniões, publicadas em redes sociais, de usuários de sistemas de processos judiciais eletrônicos (Projudi, e-SAJ, PJe e e-Proc). Para isso, utiliza o mais recente léxico do LIWC em Português do Brasil para obter valores referentes a componentes psicolinguísticos, observando emoções e aspectos cognitivos presentes nos textos. Resultados preliminares indicam que a metodologia adotada pode trazer informações relevantes sobre a percepção dos usuários acerca desses sistemas, podendo ser adotada no direcionamento de ações para aperfeiçoá-los.

show abstract

“…Natural language engineers have recognized this and begun applying the tools of computational linguistics to automatically detect particular kinds of text-based deception. 1 One type receiving considerable attention is opinion spam (e.g., Ott et al 2011;Feng, Banerjee, and Choi 2012;Ott et al 2013;Feng and Hirst 2013;Fornaciari and Poesio 2014;Li, et al 2014;Kim, et al 2017;Kleinberg, et al 2017;Rosso and Cagnina 2017;Narayan, Rout, and Jena 2018). Opinion spam refers to deceptive opinions in service and product reviews that are intended to influence consumer opinion.…”

Section: Automatic Deception Detectionmentioning

confidence: 99%

Using linguistically defined specific details to detect deception across domains

Vogler

Pearl

2019

Nat. Lang. Eng.

View full text Add to dashboard Cite

Current automatic deception detection approaches tend to rely on cues that are based either on specific lexical items or on linguistically abstract features that are not necessarily motivated by the psychology of deception. Notably, while approaches relying on such features can do well when the content domain is similar for training and testing, they suffer when content changes occur. We investigate new linguistically defined features that aim to capture specific details, a psychologically motivated aspect of truthful versus deceptive language that may be diagnostic across content domains. To ascertain the potential utility of these features, we evaluate them on data sets representing a broad sample of deceptive language, including hotel reviews, opinions about emotionally charged topics, and answers to job interview questions. We additionally evaluate these features as part of a deception detection classifier. We find that these linguistically defined specific detail features are most useful for cross-domain deception detection when the training data differ significantly in content from the test data, and particularly benefit classification accuracy on deceptive documents. We discuss implications of our results for general-purpose approaches to deception detection.

show abstract

Review Spam Detection Using Opinion Mining

Cited by 19 publications

References 8 publications

An enhanced feature‐based sentiment analysis approach

An enhanced feature‐based sentiment analysis approach

Mineração de Opiniões com LIWC: abordagem prática sobre sistemas judiciais eletrônicos brasileiros

Using linguistically defined specific details to detect deception across domains

Contact Info

Product

Resources

About