ItemArticle

AdaptiveNet: A Novel Architecture for Reducing Computation Complexity to Fake Review Classification

Title
AdaptiveNet: A Novel Architecture for Reducing Computation Complexity to Fake Review Classification
Creator
Perumalsamy, Deepalakshmi; Cornelius, Sharon Roji Priya; Thinakaran, Rajermani
Description
The exponential rise of e-commerce platforms has resulted in a dramatic increase in online reviews, which creates a challenge in distinguishing fake reviews that erode consumer confidence and harm commerce ecosystems. Traditional approaches for fake review detection employ computationally expensive deep learning networks which are resource-intensive and difficult to use in practice. In this paper, we describe AdaptiveNet, a new lightweight neural architecture that achieves fake review detection with much lower computational resources while maintaining a higher detection and classification precision. The model proposed in this paper is based on three original innovations: a Multi-Scale Semantic Fusion (MSSF) layer for hierarchical feature extraction, Dynamic Attention Scaling (DAS) with complexity measure attention, and Adaptive Parameter Sharing (APS) context-gated networks. With thorough evaluation on Amazon, Yelp, and TripAdvisor datasets of reviews totalling 1.2 million reviews, AdaptiveNet attains 94.8% accuracy while achieving 65% computational overhead in comparison to traditional models. The architecture outperformed all other state-of-the-art models, BERT-base (92.1%), RoBERTa (91.8%), and other more recent efficient models, requiring 70% lower parameters and 60% lower energy consumption. This work markedly advances the other efficient deep learning architectures for text classification and allows for the practical implementation of fake review detection systems in resource-limited settings as process innovation. 2026 by the authors.
Source
Information (Switzerland);Volume;17;Issue;4;Article No.;388;
Date
01-01-2026
Publisher
Multidisciplinary Digital Publishing Institute (MDPI)
Subject
computational efficiency; dynamic attention; fake review detection; lightweight neural networks; multi-scale feature fusion; natural language processing; parameter sharing; text classification
Coverage
Perumalsamy D., Department of Computer Science and Engineering, Kalasalingam Academy of Research and Education, Krishnankoil, 626126, India; Cornelius S.R.P., Department of Computer Science and Engineering, School of Engineering and Technology, CHRIST University, Bangalore, 560074, India; Thinakaran R., Faculty of Data Science and Information Technology, INTI International University, Negeri Sembilan, 71800, Malaysia
Rights
All Open Access; Gold Open Access; Green Open Access
Relation
ISSN: 20782489;
Format
online
Language
English
Type
Article

Citation

Perumalsamy, Deepalakshmi; Cornelius, Sharon Roji Priya; Thinakaran, Rajermani, “AdaptiveNet: A Novel Architecture for Reducing Computation Complexity to Fake Review Classification,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 18, 2026, https://archives.christuniversity.in/items/show/23531.

Output Formats