Author name cluster

Xingkong Ma

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

1 author row

EAAI Journal 2026 Journal Article

BeLink: Behavior graph network for unsupervised user identity linkage

Xingkong Ma
Mengmeng Guo
Houjie Qiu
Yiqing Cai

With the development and rise of online social networks (OSNs), the user identity linkage (UIL) task has become a focal point in recent years, which aims to match accounts belonging to the same individual across different platforms. However, most efforts in UIL are based on labeled data or social graphs, which are frequently unavailable due to privacy or access constraints. Moreover, existing methods fail to address the need for fine-grained user behavior modeling for the UIL task. To address these challenges, we propose BeLink, an unsupervised UIL framework centered on a novel behavior graph construction mechanism. Our method is based on the insight of behavioral self-similarity that individuals often exhibit consistent behavior patterns across time and platforms. To capture behavioral consistency, we construct a user behavior graph for each pair of cross-platform users, where nodes represent short-term user activity segments, and edges encode their semantic correlations. To ensure an accurate representation of nodes, we first introduce a large language model (LLM) based textual apparent analysis that resolves cross-platform inconsistencies and unifies semantic content. Subsequently, we pretrain a behavior representation model on users’ self-behavior sequences to embed activities into a unified semantic space. To infer identity linkage, BeLink employs graph-based clustering and an entropy-weighted co-occurrence scoring mechanism. Experiments on real-world datasets demonstrate that BeLink effectively links user identities using only behavioral signals, achieving an average improvement of 11. 0% in hit rate at rank 1 (Hit@1) and 14. 7% in mean reciprocal rank (MRR), and consistently outperforms all baselines.

Details DOI

AAAI Conference 2026 Conference Paper

ProRec-Video: Guiding Hierarchical Interest Transitions for Proactive Short Video Recommendation with Dynamic Feedback Adaptation

Weizhi Chen
Baoyun Peng
Bo Liu
Xingkong Ma
Houjie Qiu

Traditional short video recommendations primarily enhance user retention by reinforcing existing user preferences, potentially leading to information cocoons. Conversely, proactive recommendations aim to diversify user interests by exposing users to content beyond their historical preferences. However, current proactive approaches face three limitations: (1) homogeneous receptivity assumption, neglecting individual differences in users' openness to new interests; (2) short-term item exposure without interest anchoring, focusing on item-level shifts rather than interest evolution; and (3) static feedback utilization, failing to incorporate dynamic user feedback during the recommendation adequately. To address these challenges, we propose ProRec-Video, a proactive framework that guides hierarchical interest transitions through three innovations. First, User Receptivity Profiling assesses individual openness for new interests, ensuring personalized transition pacing. Second, Hierarchical Interest Transition Planning decomposes complex interest shifts into intermediate steps to generate smooth interest transition paths and semantically coherent video sequences, addressing overemphasis on item exposure. Third, Dynamic Feedback Adaptation integrates agent-based simulation and Reflexion mechanisms to refine interest transition paths and video sequences based on real-time user feedback, enhancing adaptability and satisfaction. Extensive experiments on two datasets demonstrate that ProRec-Video achieves a significant improvement in proactive recommendation performance, with an interest transition success rate of 85% and a user satisfaction rate of 78.3%.

PDF Details DOI