arXiv subjects

Linjiang Guo

Publications and source records attributed to Linjiang Guo.

3 recordsLinked to original sources

arXiv2026

TRUST: Item-Calibrated Interval Evidence for Temporal Session-Based Recommendation

Temporal signals have been widely used in session-based recommendation to infer user interest. Existing temporal session-based recommenders primarily rely on absolute interval values, implicitly assuming that the same interval carries similar interest signals across items. However, we empirically find that this assumption does not hold: each item has its own interval distribution, so an interval should be interpreted relative to the item it belongs to. Based on this observation, we propose TRUST, a framework that evaluates each observed interval relative to the empirical interval distribution of the corresponding item. Specifically, we propose a score function to guide global neighbor sampling, session graph encoding, and final interest aggregation. Experiments on public datasets show that TRUST consistently improves over representative temporal and non-temporal baselines, and plug-in experiments further show that the proposed scoring function can improve existing temporal session recommenders as a model-agnostic method. Component-wise ablations further show that calibrating the temporal signals within each module, rather than removing the module itself, consistently improves neighbor sampling, session graph encoding, and interest aggregation.

cs.IR↗

arXiv2026

S2-CAR: Segmentation-Supervised Complexity-Adaptive Recommendation

Sequential recommendation aims to predict user preferences from interaction histories, yet existing models often struggle when behavior patterns become complex and heterogeneous. A key reason is that interaction histories are rarely uniform: users' interests shift in a latent way over time, yet existing models either treat the full sequence as a homogeneous context or rely on rigid time-window segmentation that misaligns with true intent boundaries. This mis-segmentation not only introduces cross-intent interference at intermediate sequence positions but also leads to over-reliance on short-term interest signals. To address this, we propose S2-CAR, a segmentation-supervised and complexity-adaptive framework for sequential recommendation that models user intent as a continuous latent energy state. Specifically, it uses the Context-Aware Soft Temporal Point Process (Soft-TPP) to segment boundaries triggered by the natural decay of latent-state energy rather than fixed intervals, enabling intent segmentation without fixed time-gap rules. Next, upon this segmentation, a Segment-Count-Adaptive Multi-Intent Extraction module hierarchically aggregates intent-coherent segments into a compact set of multi-interest representations. Extensive experiments on 3 representative public benchmark datasets spanning movie, e-commerce, and gaming domains across 13 baselines demonstrate that S2-CAR consistently outperforms state-of-the-art methods across all datasets and metrics. Further analysis shows that the proposed energy-based segmentation serves as a plug-and-play module, yielding consistent improvements when integrated into existing sequential recommendation backbones.

cs.IR↗

arXiv2022

Coronavirus statistics causes emotional bias: a social media text mining perspective

While COVID-19 has impacted humans for a long time, people search the web for pandemic-related information, causing anxiety. From a theoretic perspective, previous studies have confirmed that the number of COVID-19 cases can cause negative emotions, but how statistics of different dimensions, such as the number of imported cases, the number of local cases, and the number of government-designated lockdown zones, stimulate people's emotions requires detailed understanding. In order to obtain the views of people on COVID-19, this paper first proposes a deep learning model which classifies texts related to the pandemic from text data with place labels. Next, it conducts a sentiment analysis based on multi-task learning. Finally, it carries out a fixed-effect panel regression with outputs of the sentiment analysis. The performance of the algorithm shows a promising result. The empirical study demonstrates while the number of local cases is positively associated with risk perception, the number of imported cases is negatively associated with confidence levels, which explains why citizens tend to ascribe the protracted pandemic to foreign factors. Besides, this study finds that previous pandemic hits cities recover slowly from the suffering, while local governments' spending on healthcare can improve the situation. Our study illustrates the reasons for risk perception and confidence based on different sources of statistical information due to cognitive bias. It complements the knowledge related to epidemic information. It also contributes to a framework that combines sentiment analysis using advanced deep learning technology with the empirical regression method.

cs.CY↗