Paper Type
Complete
Paper Number
1440
Description
Fake reviews pose a significant threat to business practices, which has been exacerbated in recent years by factors such as the surge in online commerce or consumer-oriented generative AI. Despite awareness of the economic damage caused by fake reviews, it is not yet common practice to implement appropriate detection mechanisms. In this study, we contribute to the research and practical application of fake review detection by providing a multifactorial overview of classification performance, hardware utilization, and method interpretability across various hardware settings. Following an experimental research approach, we demonstrate that the barriers to SME digitization need not hinder the implementation of effective measures to safeguard the digital business practices of these companies. Through the utilization of reproducible feature engineering, baseline models, and comparison of results across various hardware configurations, we demonstrate the feasibility of developing a dedicated service for SME in electronic commerce requiring few resources.
Recommended Citation
Theuerkauf, René and Peters, Ralf, "Fake Review Detection on a Budget – Feasibility and Configuration for SME" (2024). PACIS 2024 Proceedings. 8.
https://aisel.aisnet.org/pacis2024/track17_socmedia/track17_socmedia/8
Fake Review Detection on a Budget – Feasibility and Configuration for SME
Fake reviews pose a significant threat to business practices, which has been exacerbated in recent years by factors such as the surge in online commerce or consumer-oriented generative AI. Despite awareness of the economic damage caused by fake reviews, it is not yet common practice to implement appropriate detection mechanisms. In this study, we contribute to the research and practical application of fake review detection by providing a multifactorial overview of classification performance, hardware utilization, and method interpretability across various hardware settings. Following an experimental research approach, we demonstrate that the barriers to SME digitization need not hinder the implementation of effective measures to safeguard the digital business practices of these companies. Through the utilization of reproducible feature engineering, baseline models, and comparison of results across various hardware configurations, we demonstrate the feasibility of developing a dedicated service for SME in electronic commerce requiring few resources.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
Social