Article
Business
Sule Ozturk Birim, Ipek Kazancoglu, Sachin Kumar Mangla, Aysun Kahraman, Satish Kumar, Yigit Kazancoglu
Summary: Consumers can greatly benefit from reading online product reviews to counter the uncertainty caused by information overload in the online world. However, some reviews are deceptively written to manipulate purchasing decisions. This study aims to determine the most effective feature combination for detecting fake reviews, including sentiment scores, topic distributions, cluster distributions, and bag of words. The results suggest that behavior-related features, particularly verified purchases, play a crucial role in accurately classifying fake reviews in conjunction with text-related features.
JOURNAL OF BUSINESS RESEARCH
(2022)
Article
Computer Science, Artificial Intelligence
Mohammad Hadi Goldani, Saeedeh Momtazi, Reza Safabakhsh
Summary: The paper explores the use of capsule neural networks for fake news detection, utilizing different embedding models and n-gram levels for feature extraction. Experimental results on the ISOT and LIAR datasets show promising performance compared to state-of-the-art methods.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Kai Shu, Susan Dumais, Ahmed Hassan Awadallah, Huan Liu
Summary: Limited labeled data pose a challenge for supervised learning systems, but weak supervision, especially weak social supervision from social media, can help mitigate this issue. This article demonstrates the effectiveness of weak social supervision, using fake news detection research as a case study, in tasks where annotated examples are scarce but social engagements are abundant. This opens up possibilities for utilizing weak social supervision in similar tasks with limited labeled data.
IEEE INTELLIGENT SYSTEMS
(2021)
Article
Computer Science, Information Systems
Wesam Shishah
Summary: The rapid rise of social media has led to an increase in fake rumors in Arab countries, posing potential harm to individuals and society. To address this issue, researchers have developed a revolutionary algorithm using the BERT model to detect Arabic fake news accurately.
Article
Computer Science, Theory & Methods
Jiachen Yang, Shuai Xiao, Aiyun Li, Guipeng Lan, Huihui Wang
Summary: Fake detection has become an urgent task. The rapid development of Deepfake technology poses a threat to network security. This paper proposes an intelligent forensic method for Deepfake detection, achieving state-of-the-art detection accuracy.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2021)
Article
Business
Joni Salminen, Chandrashekhar Kandpal, Ahmed Mohamed Kamel, Soon-gyo Jung, Bernard J. Jansen
Summary: The study found that machines are more suitable for detecting fake reviews than humans, as machine classifiers can almost perfectly accomplish this task. The detection of fake reviews has important implications for consumer protection, competition defense for firms, and the responsibility of review platforms.
JOURNAL OF RETAILING AND CONSUMER SERVICES
(2022)
Article
Public, Environmental & Occupational Health
Suleman Khan, Saqib Hakak, N. Deepa, B. Prabadevi, Kapal Dev, Silvia Trelova
Summary: Since December 2019, there has been an abundance of posts and news about the COVID-19 pandemic on social media, traditional print, and electronic media, which may lead to anxiety and unnecessary exposure to medical remedies. In response to this issue, the author used a dataset fused from multiple sources and trained several machine learning algorithms for classifying COVID-19 related news after preprocessing, tokenization, and feature selection steps. The results showed that the random forest classifier performed the best with an accuracy of 88.50%.
FRONTIERS IN PUBLIC HEALTH
(2022)
Article
Multidisciplinary Sciences
Stephanie Preston, Anthony Anderson, David J. Robertson, Mark P. Shephard, Narisong Huhe
Summary: The spread of fake news on social media has raised significant concerns, with studies showing that individuals with higher emotional intelligence and education levels are better at detecting fake news. Further research is needed on combating false acceptance of fake news to protect public health and democratic processes.
Article
Multidisciplinary Sciences
K. Peren Arin, Deni Mazrekaj, Marcel Thum
Summary: By conducting large-scale surveys in Germany and the United Kingdom, the study examines the factors that influence individuals' ability to detect fake news and their tendency to share it, distinguishing between deliberate and accidental sharing. The findings suggest that accidental sharing is more common than deliberate sharing, and that older, male, high-income, and politically left-leaning respondents are better at detecting fake news. Additionally, accidental sharing decreases with age and is more prevalent among right-leaning respondents, while deliberate sharing of fake news is more prevalent among younger respondents in the United Kingdom. Furthermore, the results indicate that respondents have a good assessment of their ability to detect fake news, as those identified as accidental sharers were more likely to admit to having shared fake news.
SCIENTIFIC REPORTS
(2023)
Review
Multidisciplinary Sciences
Sherry He, Brett Hollenbeck, Gijs Overgoor, Davide Proserpio, Ali Tosyali
Summary: Online reviews have a significant impact on consumer decision-making and firm economic outcomes. Fake reviews have become a prevalent issue, and despite academic research and platform efforts, their prevalence continues to rise. This study tackles the issue by collecting a dataset of Amazon product reviews and developing a highly accurate method for detecting fake reviews. By directly observing which sellers buy fake reviews, the researchers successfully identify patterns in the product reviewer network that can predict fake review buyers. The network-based approach proves to be more robust to manipulation compared to text or metadata-based methods.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2022)
Article
Chemistry, Multidisciplinary
Pawel Gryka, Artur Janicki
Summary: Many customers rely on online reviews to make informed decisions, but fake reviews are becoming increasingly common, leading to a need for effective detection methods. This article presents a case study on detecting fake reviews in Google Maps places in Poland. The study includes the construction and validation of a dataset containing 18 thousand fake and genuine reviews, and the training of machine learning models to detect fake reviews and accounts. The results show promising initial recognition scores and can contribute to future research on detecting fake reviews on the Internet.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Junxiao Xue, Yabo Wang, Yichen Tian, Yafei Li, Lei Shi, Lin Wei
Summary: This study introduces a Multimodal Consistency Neural Network (MCNN) for detecting fake news, which consists of five subnetworks extracting features from text and image to measure and fuse the similarity of multimodal data.
INFORMATION PROCESSING & MANAGEMENT
(2021)
Article
Computer Science, Information Systems
Eman Elsaeed, Osama Ouda, Mohammed M. Elmogy, Ahmed Atwan, Eman El-Daydamony
Summary: The proliferation of social media and blogs has led to the spread of fake news, highlighting the importance of utilizing machine learning algorithms for detection. A framework based on feature extraction and selection algorithms was proposed, evaluated using multiple datasets and performance metrics.
Article
Computer Science, Artificial Intelligence
Bailin Xie, Qi Li
Summary: Social network users are not only news disseminators and consumers, but also gatekeepers. This study introduces the concept of gatekeepers into social network fake news detection and proposes a recurrent neural network (RNN) based gatekeeping behavior model (RGBM). The proposed method can detect social network fake news in real time and achieved high accuracy, recall, and F1 score in experiments on Twitter and Weibo datasets. It outperformed several state-of-the-art approaches and showed effectiveness in detecting fake news in early and middle stages of news propagation.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Yuhang Wang, Li Wang, Yanjie Yang, Yilin Zhang
Summary: Due to the data collection problem, methods based on propagation and user profiles are less applicable in the early stages of fake news detection. In this paper, a multi-EDU-structure awareness model called EDU4FD is proposed to enhance text representation for fake news detection. Experimental results show that the model outperforms the state-of-the-art text-based methods, indicating the importance of considering the granularity of EDU and its structural features for fake news detection.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)