Despite increasing research on product rating prediction, very few studies have considered user-item interaction relationships at multiple levels. To address this critical limitation, we propose a novel rating prediction method based on multi-interaction attention (RPMIA) by learning user-item interaction relationships at three levels simultaneously from online consumer reviews for predicting product ratings with reasonable interpretability. Specifically, RPMIA first deploys a multihead cross-attention mechanism to capture the interaction between contexts of items and users. Then, it uses a bilayer gate-based mechanism to extract the aspects of items and users and a self-attention mechanism to learn their interaction at the aspect level. Finally, the aspects of users and items are coupled together to form meaningful user-item aspect pairs via a joint attention. A multitask predictor that integrates a factorization machine and a feedforward neural network is designed to generate a rating prediction. We empirically evaluated RPMIA with seven real-world data sets. The results demonstrate that RPMIA outperforms the state-of-the-art methods consistently and significantly. We also conduct a user study to assess the interpretability of the RPMIA method. History: Accepted by Ram Ramesh, Area Editor for Data Science & Machine Learning. Funding: The research is supported by Beijing Social Science Foundation [24XCB012], Suzhou Key Laboratory of Artificial Intelligence and Social Governance Technologies [SZS2023007], and Smart Social Governance Technology and Innovative Application Platform [YZCXPT2023101]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2023.0131 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2023.0131 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .

Offensive language is a significant detriment to social media environments. Existing research predominantly assumes monolingual expression, overlooking the prevalent behavior of code-switching (CS). To address this critical knowledge gap, this study identifies and empirically validates the distinct stylometric characteristics of code-switched (CSed) offensive language. Additionally, we developed methods to construct the first social media dataset specifically for CSed offensive content. Our analysis of this dataset reveals that CSed offensive language exhibits unique stylometric characteristics; moreover, these characteristics vary between the language segments involved in the CS. Furthermore, incorporating these features significantly enhances the performance of offensive language detection models. These findings offer significant research and practical implications for social media researchers, platforms, moderators, and users.

Serendipity means unexpected discoveries that are valuable, with positive outcomes ranging from personal benefits to scientific breakthroughs. This study proposes a cross-domain recommendation model, called SerenCDR , to model serendipity. SerenCDR leverages the knowledge beyond one domain as well as mitigates the inherent data sparsity problem in serendipity recommendations. The novelty of SerenCDR lies in the fact that it is the first deep learning based cross-domain model for a serendipity task. More importantly, it does not rely on any overlapping users or overlapping items across different domains, which especially fits for the task of recommending serendipity, because serendipity in a single domain tends to be sparse; finding overlapping users or overlapping items in other domains is nearly impossible. To train and test SerenCDR , we have collected a two-domain ground truth dataset on serendipity, called SerenCDRLens . In addition, since we found that serendipity is sparse in SerenCDRLens , we designed an auxiliary loss function to supplement the main loss function to enhance serendipity learning. Through a series of experiments, we have harvested positive performance in recommending serendipity, empowering users with increased chances of bumping into unexpected but valuable discoveries.

Today’s recommender systems are criticized for recommending items that are too obvious to arouse users’ interests. Therefore, the research community has advocated some “beyond accuracy” evaluation metrics such as novelty, diversity, and serendipity with the hope of promoting information discovery and sustaining users’ interests over a long period of time. While bringing in new perspectives, most of these evaluation metrics have not considered individual users’ differences in their capacity to experience those “beyond accuracy” items. Open-minded users may embrace a wider range of recommendations than conservative users. In this article, we proposed to use curiosity traits to capture such individual users’ differences. We developed a model to approximate an individual’s curiosity distribution over different stimulus levels. We used an item’s surprise level to estimate the stimulus level and whether such a level is in the range of the user’s appetite for stimulus, called Comfort Zone . We then proposed a recommender system framework that considers both user preference and their Comfort Zone where the curiosity is maximally aroused. Our framework differs from a typical recommender system in that it leverages human’s Comfort Zone for stimuli to promote engagement with the system. A series of evaluation experiments have been conducted to show that our framework is able to rank higher the items with not only high ratings but also high curiosity stimulation. The recommendation list generated by our algorithm has a higher potential of inspiring user curiosity compared to the state-of-the-art deep learning approaches. The personalization factor for assessing the surprise stimulus levels further helps the recommender model achieve smaller (better) inter-user similarity.

The recent California Consumer Privacy Act (CCPA) requires that personal data shall be limited to what is necessary for business purposes. Business services shall “implement technical safeguards that prohibit re-identification of the consumer to whom the information may pertain”. For recommender systems, we believe the legal concepts of limitation and technical safeguard are not specific enough to operationalize in practice. This study makes efforts to map the legislative challenges to practice of reducing personal data. More importantly, we borrowed the notion of uncertainty from the machine learning community, and added it as another aspect of recommendation utility, in addition to recommendation accuracy, to guide the data reduction process. The benefit of using uncertainty is that we have more comprehensive consideration while reducing the personal data. In addition, two major types of uncertainty in machine learning models: aleatoric uncertainty and epistemic uncertainty, helped us formulate two groups of data reduction strategies: within-user and between-user. We conducted a series of analyses regarding uncertainty change and accuracy loss caused by different data reduction strategies. We found that at the aggregate level, data reduction is feasible with certain data reduction strategies. At the individual level, the recommendation utility (both uncertainty and accuracy) loss incurred by data reduction disparately impacts different users — a finding which has implications for fairness and transparency of AI models. Our results reveal the difficulty and intricacy of the data reduction problem in the context of recommender systems.

Serendipity is a notion that means an unexpected but valuable discovery. Due to its elusive and subjective nature, serendipity is difficult to study even with today's advances in machine learning and deep learning techniques. Both ground truth data collecting and model developing are the open research questions. This paper addresses both the data and the model challenges for identifying serendipity in recommender systems. For the ground truth data collecting, it proposes a new and scalable approach by using both user generated reviews and a crowd sourcing method. The result is a large-scale ground truth data on serendipity. For model developing, it designed a self-enhanced module to learn the fine-grained facets of serendipity in order to mitigate the inherent data sparsity problem in any serendipity ground truth dataset. The self-enhanced module is general enough to be applied with many base deep learning models for serendipity. A series of experiments have been conducted. As the result, a base deep learning model trained on our collected ground truth data, as well as with the help of the self-enhanced module, outperforms the state-of-the-art baseline models in predicting serendipity.

As the popularity of online travel platforms increases, users tend to make ad-hoc decisions on places to visit rather than preparing the detailed tour plans in advance. Under the situation of timeliness and uncertainty of users’ demand, how to integrate real-time context into dynamic and personalized recommendations have become a key issue in travel recommender system. In this article, by integrating the users’ historical preferences and real-time context, a location-aware recommender system called TRACE ( T ravel R einforcement Recommendations Based on Location- A ware C ontext E xtraction) is proposed. It captures users’ features based on location-aware context learning model, and makes dynamic recommendations based on reinforcement learning. Specifically, this research: (1) designs a travel reinforcing recommender system based on an Actor-Critic framework, which can dynamically track the user preference shifts and optimize the recommender system performance; (2) proposes a location-aware context learning model, which aims at extracting user context from real-time location and then calculating the impacts of nearby attractions on users’ preferences; and (3) conducts both offline and online experiments. Our proposed model achieves the best performance in both of the two experiments, which demonstrates that tracking the users’ preference shifts based on real-time location is valuable for improving the recommendation results.