Spam review detection using LSTM autoencoder: an unsupervised approach

The review of online products or services is becoming a major factor in the user’s purchasing decisions. The popularity and influence of online reviews attract spammers who intend to elevate their products or services by writing positive reviews for them and lowering the business of others by writin...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Electronic commerce research Jg. 22; H. 1; S. 113 - 133
Hauptverfasser: Saumya, Sunil, Singh, Jyoti Prakash
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York Springer US 01.03.2022
Springer
Springer Nature B.V
Schlagworte:
Business and Management
Classification
Computer Communication Networks
Data Structures and Information Theory
Datasets
e-Commerce/e-business
IT in Business
Machine learning
Operations Research/Decision Theory
Spam (Junk email)
Unsupervised learning
Long short-term memory
E-commerce
Autoencoder neural network
Spam detection
Unsupervised learning
Machine learning
ISSN:1389-5753, 1572-9362
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The review of online products or services is becoming a major factor in the user’s purchasing decisions. The popularity and influence of online reviews attract spammers who intend to elevate their products or services by writing positive reviews for them and lowering the business of others by writing negative reviews. Traditionally, the spam review identification task is seen as a two-class classification problem. The classification approach requires a labelled dataset to train a model for the environment it is working on. The unavailability of the labelled dataset is a major limitation in the classification approach. To overcome the problem of the labelled dataset, we propose an unsupervised learning model combining long short-term memory (LSTM) networks and autoencoder (LSTM-autoencoder) to distinguish spam reviews from other real reviews. The said model is trained to learn the patterns of real review from the review’s textual details without any label. The experimental results show that our model is able to separate the real and spam review with good accuracy.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1389-5753
1572-9362
DOI:10.1007/s10660-020-09413-4