Travel recommendation aims to infer travel intentions of users by analyzing their historical behaviors on Online Travel Agencies (OTAs). However, crucial keywords in clicked travel product titles, such as destination and itinerary duration, ...

• Keywords in title are treated as an additional supervision signal to improve recommendation quality.
• Long-term and short-term user preferences are learned from historical and current sessions.
• Two types of contrastive learning help ...

Using the user’s past activity across different domains, the cross-domain recommendation (CDR) predicts the items that users are likely to click. Most recent studies on CDR model user interests at the item level. However because items in other ...

• A cross-domain recommendation method with intention disentanglement and contrast is proposed.
• Intention disentanglement module helps comprehensively represent the user’s purpose for interacting with an item.
• Intention contrastive ...

Cross-platform User Alignment (UA) aims to identify accounts belonging to the same individual across multiple social network platforms. This study seeks to enhance the performance of UA tasks while reducing the required sample data. Previous ...

As the volume of submitted papers continues to rise, ensuring a fair and accurate assignment of manuscripts to reviewers has become increasingly critical for academic conference organizers. Given the paper-reviewer similarity scores, this study ...

• Individual relative fairness in the Reviewer Assignment Problem is introduced.
• A novel formulation of the Reviewer Assignment Problem as a Coloring Problem.
• Necessary conditions for feasible, fair and balanced assignments are ...

• The model learns the latent stakeholders’ preferences by embedding multi-view information sources.
• A personalized preference evaluation model is developed for each stakeholder to satisfy their goals.
• The stakeholders’ preferences ...

Learning the preferences of consumers, providers, and system stakeholders is a challenging problem in the Multi-Stakeholder Recommendation System (MSRS). Existing MSRS methods lack the ability to generate equitable recommendations and investigate ...

The serious information overload problem of MOOCs videos decreases the learning efficiency of the students and the utilization rate of the videos. There are two problems worthy of attention for the matrix factorization (MF)-based video ...

Topic evolution has been studied extensively in the field of the science of science. This study first analyzes topic evolution pattern from topics’ semantic consistency in the semantic vector space, and explore its possible causes. Specifically, ...

Existing personalized federated learning frameworks fail to significantly improve the personalization of user preference learning in next Point-Of-Interest (POI) recommendations, causing notable performance deficits. These frameworks do not fully ...

• We introduce ChatGPT paraphrased reviews as a new challenge for online fake reviews.
• We study the association/disassociation between real and paraphrased reviews.
• We identify a consistent association/disassociation pattern.
• ...

Fake reviews corrode the trust between businesses and consumers and distort the online image of a service or a product. The problem of fake review contamination is only going to worsen with the introduction of Artificial Intelligence (AI) ...

Personalization is a prominent process in today’s recommender systems (RS) that enhances user satisfaction and platform profitability. However, recent studies suggest that over-personalization may lead to polarized user preferences, which can ...

• We propose three DQN methods for controlling user polarization in recommendations.
• ICDQN is a hard-constrained method that limits the increase in user polarization.
• RP-DQN is a soft-constrained method that penalizes polarizing item ...

During mobile application development, developers often use various third-party libraries to expedite the development process and enhance application functionality. Real datasets often show significant long-tailed distribution characteristics, ...

• We propose a TPL recommendation model based on homogeneous graph neural networks.
• HGNRec splits the interaction information into two homogeneous graph.
• We incorporate a statistically-based edge construction for node aggregation.

Fake news detection involves developing techniques to identify and flag misleading or false information disseminated through media sources. Current efforts often use limited information for categorization, lacking comprehensive data integration ...

• We propose a novel Multifaceted Reasoning Network for Explainable Fake News Detection.
• We integrate multi-source and multi-granularity information, and provide multi-angle explanations for fake news classification.
• We conducted ...

• We utilize large-scale scholarly datasets to quantify the duration of peer review process for interdisciplinary research.
• Contrary to the widely observed notion that interdisciplinary research often has long-term impact, we find that ...

With the growing prominence of interdisciplinary research and heightened concerns surrounding extended prepublication timelines, we still lack of understanding regarding the interplay between interdisciplinary level and the duration of the peer ...

The objective of the Aspect Sentiment Triplet Extraction (ASTE) task is to identify triplets of (aspect, opinion, sentiment) from user-generated reviews. The current study does not extensively integrate the interaction between word pairs and ...

• We develop SBRS for ASTE to effectively address the problem of overlapping triplets.
• SBRS designs two progressive word levels and word pair levels to refine the text.
• SBRS utilize transfer of temporal semantic information through ...

This study presents a financial distress prediction model focusing on the linguistic analysis of risk-related sections of corporate annual reports. Here, we introduce a novel methodology that leverages BERT-based contextualized embedding models ...

• Linguistic analysis of risk-related sections of corporate annual reports.
• BERT-based models used to identify financial sentiment and coherent topics.
• A semi-supervised XGBoost approach used to predict financial distress.
• ...

• Entrepreneurs’ responses on crowdfunding financing are monetized.
• Response strategies are classified into project-oriented and investor-oriented.
• Project-oriented responses are favored than investor-oriented.
• Commenters prefer ...

This paper examines the role of response in crowdfunding to guide fundraisers to monetize their responses better. In all, 6,405 commenters on a large crowdfunding platform in China (Modian.com) are observed. Grounded on the interaction texts, we ...

The personalized bundle generation problem, which aims to create a preferred bundle for user from numerous candidate items, receives increasing attention in recommendation. However, existing works ignore the order-invariant nature of the bundle ...

• The bundle generation task is formulated via non-autoregressive mechanism.
• A GNN-based positional encoding module is designed to better capture dependency pattern for the bundle.
• A permutation-equivariant decoder can output the ...

Existing benchmarks for Large Language Models (LLMs) mostly focus on general or specific domain capabilities, overlooking structured output capabilities. We introduce SoEval, a benchmark for assessing LLMs’ ability to generate structured outputs ...

• Introducing a novel benchmark for assessing the ability of LLMs to produce structured outputs.
• Presenting a theoretical foundation by analyzing prompt structures and causal graph analysis.
• We Develop the SoEval dataset for 20 ...

• A novel multi-domain fake news detection model is proposed for domain generalization in fake news detection.
• Entities in news articles are key to learning both domain-invariant and domain-specific news representations.
• We introduce ...

Fake news has become a significant concern in recent times, particularly during the COVID-19 pandemic, as spreading false information can pose significant public health risks. Although many models have been suggested to detect fake news, they are ...

Medical Visual Question Answering (MedVQA) is designed to answer natural language questions related to medical images. Existing methods largely adopting the cross-modal pre-training and fine-tuning paradigm, face limitations in accuracy due to ...