More Like this

1. Applying large language models to sanitize self-disclosure in user-generated content

   https://doi.org/10.1016/j.asoc.2025.113311  

   Alfieri, Costanza; Scoccia, Gian Luca; Ganesh, Surya; Sadeh, Norman (June 2025, Applied Soft Computing)

   The rise of e-commerce and social networking platforms has led to an increase in the disclosure of personal health information within user-generated content. This study investigates the application of large language models (LLMs) to detect and sanitize sensitive health data shared by users across platforms such as Amazon, patient.info, and Facebook. We propose a methodology that leverages LLMs to evaluate both the sensitivity of disclosed information and the platform-specific semantics of the content. Through prompt engineering, our method identifies sensitive information and rephrases it to minimize disclosure while preserving content similarity. ChatGPT serves as the LLM in this study due to its versatility. Empirical results suggest that ChatGPT can reliably assign sensitivity scores to user-generated text and generate sanitized versions that effectively preserve the original meaning. 

   more » « less
2. Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews.

   Liang, Weixin; Izzo, Zachary; Zhang, Yaohui; Lepp, Haley; Cao, Hancheng; Zhao, Xuandong; Chen, Lingjiao; Ye, Haotian; Liu, Sheng; Huang, Zhi; et al (July 2024, ICML conference.)

   We present an approach for estimating the fraction of text in a large corpus which is likely to be substantially modified or produced by a large language model (LLM). Our maximum likelihood model leverages expert-written and AI-generated reference texts to accurately and efficiently examine real-world LLM-use at the corpus level. We apply this approach to a case study of scientific peer review in AI conferences that took place after the release of ChatGPT: ICLR 2024, NeurIPS 2023, CoRL 2023 and EMNLP 2023. Our results suggest that between 6.5% and 16.9% of text submitted as peer reviews to these conferences could have been substantially modified by LLMs, i.e. beyond spell-checking or minor writing updates. The circumstances in which generated text occurs offer insight into user behavior: the estimated fraction of LLM-generated text is higher in reviews which report lower confidence, were submitted close to the deadline, and from reviewers who are less likely to respond to author rebuttals. We also observe corpus-level trends in generated text which may be too subtle to detect at the individual level, and discuss the implications of such trends on peer review. We call for future interdisciplinary work to examine how LLM use is changing our information and knowledge practices. 

   more » « less
3. The FacT: Taming Latent Factor Models for Explainability with Factorization Trees

   https://doi.org/10.1145/3331184.3331244  

   Tao, Yiyi; Jia, Yiling; Wang, Nan; Wang, Hongning (July 2019, Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval)

   Latent factor models have achieved great success in personalized recommendations, but they are also notoriously difficult to explain. In this work, we integrate regression trees to guide the learning of latent factor models for recommendation, and use the learnt tree structure to explain the resulting latent factors. Specifically, we build regression trees on users and items respectively with user-generated reviews, and associate a latent profile to each node on the trees to represent users and items. With the growth of regression tree, the latent factors are gradually refined under the regularization imposed by the tree structure. As a result, we are able to track the creation of latent profiles by looking into the path of each factor on regression trees, which thus serves as an explanation for the resulting recommendations. Extensive experiments on two large collections of Amazon and Yelp reviews demonstrate the advantage of our model over several competitive baseline algorithms. Besides, our extensive user study also confirms the practical value of explainable recommendations generated by our model. 

   more » « less
4. Aspect Category Detection in Product Reviews using Contextual Representation

   Ramezani, S.; Rahimi, R.; Allan, J. (July 2020, Proceedings of ACM SIGIR Workshop on eCommerce (SIGIR eCom’20))

   null (Ed.)

   Aspect category detection (ACD) is one of the challenging sub-tasks in aspect-based sentiment analysis. The goal of this task is to detect implicit or explicit aspect categories from the sentences of user-generated reviews. Since annotation over the aspects is time-consuming, the amount of labeled data is limited for super-vised learning. In this paper, we study contextual representations of reviews using the BERT model to better extract useful features from text segments in the reviews, and train a supervised classifier with a small amount of labeled data for the ACD task. Experimental results obtained on Amazon reviews of six product domains show that our method is effective in some domains. 

   more » « less
5. T-RECSYS: A Novel Music Recommendation System Using Deep Learning

   Ferdos Fessahaye, Luis Perez (January 2018, IEEE International Conference on Consumer Electronics)

   A recommendation system is a program that utilizes techniques to suggest to a user items that they would likely prefer. This paper focuses on an approach to improving music recommendation systems, although the proposed solution could be applied to many different platforms and domains, including Youtube (videos), Netflix (movies), Amazon (shopping), etc. Current systems lack adequate efficiency once more variables are introduced. Our algorithm, Tunes Recommendation System (T-RECSYS), uses a hybrid of content-based and collaborative filtering as input to a deep learning classification model to produce an accurate recommendation system with real-time prediction. We apply our approach to data obtained from the Spotify Recsys Challenge, attaining precision scores as high as 88% at a balanced discrimination threshold. 

   more » « less