An official website of the United States government
User-generated product reviews are essential for online platforms like Amazon and Yelp. However, the presence of fake reviews misleads customers. GNN is the state-of-the-art method that detects suspicious reviewers by exploiting the topologies of the graph connecting reviewers, reviews, and products. Nevertheless, the discrepancy in the detection accuracy over different groups of reviewers degrades reviewer engagement and customer trust in the review websites. Unlike the previous belief that the difference between the groups causes unfairness, we study the subgroup structures within the groups that can also cause discrepancies in treating different groups. This paper addresses the challenges of defining, approximating, and utilizing a new subgroup structure for fair spam detection. We first identify subgroup structures in the review graph that lead to discrepant accuracy in the groups. The complex dependencies over the review graph create difficulties in teasing out subgroups hidden within larger groups. We design a model that can be trained to jointly infer the hidden subgroup memberships and exploits the membership for calibrating the detection accuracy across groups. Comprehensive comparisons against baselines on three large Yelp review datasets demonstrate that the subgroup membership can be identified and exploited for group fairness.
more »
« less
A multiview clustering framework for detecting deceptive reviews
Online reviews, which play a key role in the ecosystem of nowadays business, have been the primary source of consumer opinions. Due to their importance, professional review writing services are employed for paid reviews and even being exploited to conduct opinion spam. Posting deceptive reviews could mislead customers, yield significant benefits or losses to service vendors, and erode confidence in the entire online purchasing ecosystem. In this paper, we ferret out deceptive reviews originated from professional review writing services. We do so even when reviewers leverage a number of pseudonymous identities to avoid the detection. To unveil the pseudonymous identities associated with deceptive reviewers, we leverage the multiview clustering method. This enables us to characterize the writing style of reviewers (deceptive vs normal) and cluster the reviewers based on their writing style. Furthermore, we explore different neural network models to model the writing style of deceptive reviews. We select the best performing neural network to generate the representation of reviews. We validate the effectiveness of the multiview clustering framework using real-world Amazon review data under different experimental scenarios. Our results show that our approach outperforms previous research. We further demonstrate its superiority through a large-scale case study based on publicly available Amazon datasets.
more »
« less
- Award ID(s):
- 2317829
- PAR ID:
- 10542568
- Publisher / Repository:
- IOS
- Date Published:
- Journal Name:
- Journal of Computer Security
- Volume:
- 32
- Issue:
- 1
- ISSN:
- 0926-227X
- Page Range / eLocation ID:
- 31 to 52
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Peer-review plays a critical role in the scientific writing and publication ecosystem. To assess the efficiency and efficacy of the reviewing process, one essential element is to understand and evaluate the reviews themselves. In this work, we study the content and structure of peer reviews under the argument mining framework, through automatically detecting (1) the argumentative propositions put forward by reviewers, and (2) their types (e.g., evaluating the work or making suggestions for improvement). We first collect 14.2K reviews from major machine learning and natural language processing venues. 400 reviews are annotated with 10,386 propositions and corresponding types of Evaluation, Request, Fact, Reference, or Quote. We then train state-of-the-art proposition segmentation and classification models on the data to evaluate their utilities and identify new challenges for this new domain, motivating future directions for argument mining. Further experiments show that proposition usage varies across venues in amount, type, and topic.more » « less
-
Recent advances in Large Language Models (LLMs) show the potential to significantly augment or even replace complex human writing activities. However, for complex tasks where people need to make decisions as well as write a justification, the trade offs between making work efficient and hindering decisions remain unclear. In this paper, we explore this question in the context of designing intelligent scaffolding for writing meta-reviews for an academic peer review process. We prototyped a system called MetaWriter'' trained on five years of open peer review data to support meta-reviewing. The system highlights common topics in the original peer reviews, extracts key points by each reviewer, and on request, provides a preliminary draft of a meta-review that can be further edited. To understand how novice and experienced meta-reviewers use MetaWriter, we conducted a within-subject study with 32 participants. Each participant wrote meta-reviews for two papers: one with and one without MetaWriter. We found that MetaWriter significantly expedited the authoring process and improved the coverage of meta-reviews, as rated by experts, compared to the baseline. While participants recognized the efficiency benefits, they raised concerns around trust, over-reliance, and agency. We also interviewed six paper authors to understand their opinions of using machine intelligence to support the peer review process and reported critical reflections. We discuss implications for future interactive AI writing tools to support complex synthesis work.more » « less
-
Modern machine learning and computer science conferences are experiencing a surge in the number of submissions that challenges the quality of peer review as the number of competent reviewers is growing at a much slower rate. To curb this trend and reduce the burden on reviewers, several conferences have started encouraging or even requiring authors to declare the previous submission history of their papers. Such initiatives have been met with skepticism among authors, who raise the concern about a potential bias in reviewers' recommendations induced by this information. In this work, we investigate whether reviewers exhibit a bias caused by the knowledge that the submission under review was previously rejected at a similar venue, focusing on a population of novice reviewers who constitute a large fraction of the reviewer pool in leading machine learning and computer science conferences. We design and conduct a randomized controlled trial closely replicating the relevant components of the peer-review pipeline with $133$ reviewers (master's, junior PhD students, and recent graduates of top US universities) writing reviews for $19$ papers. The analysis reveals that reviewers indeed become negatively biased when they receive a signal about paper being a resubmission, giving almost 1 point lower overall score on a 10-point Likert item (Δ = -0.78, 95% CI = [-1.30, -0.24]) than reviewers who do not receive such a signal. Looking at specific criteria scores (originality, quality, clarity and significance), we observe that novice reviewers tend to underrate quality the most.more » « less
-
This is the first of a series of studies that explore the relationship between disciplinary background and the weighting of various elements of a manuscript in peer reviewers’ determination of publication recommendations. Research questions include: (1) To what extent are tacit criteria for determining quality or value of EER manuscripts influenced by reviewers’ varied disciplinary backgrounds and levels of expertise? and (2) To what extent does mentored peer review professional development influence reviewers’ EER manuscript evaluations? Data were collected from 27 mentors and mentees in a peer review professional development program. Participants reviewed the same two manuscripts, using a form to identify strengths, weaknesses, and recommendations. Responses were coded by two researchers (70% IRR). Our findings suggest that disciplinary background influences reviewers’ evaluation of EER manuscripts. We also found evidence that professional development can improve reviewers’ understanding of EER disciplinary conventions. Deeper understanding of the epistemological basis for manuscript reviews may reveal ways to strengthen professional preparation in engineering education as well as other disciplines.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3233/JCS-220001
