Utilizing Cognitive Signals Generated during Human Reading to Enhance Keyphrase Extraction from Microblogs

2026-06-24

AI Summary

This study addresses the challenge of keyword extraction from short, noisy microblog texts and the limitations of existing eye-tracking–based approaches due to physiological and data acquisition constraints. It presents the first systematic investigation into the roles of electroencephalography (EEG) and eye-tracking cognitive signals for keyword extraction, proposing a multimodal fusion model that injects EEG features into the attention mechanism’s input and eye-tracking features into its query vectors. Evaluated on the ZuCo corpus using eight EEG and seventeen eye-tracking features with soft and self-attention mechanisms, the experiments demonstrate that EEG signals significantly enhance extraction performance—outperforming eye-tracking signals—while multimodal fusion exhibits complementary benefits yet also redundancy, yielding intermediate overall results. This work validates the efficacy of EEG in natural language processing tasks and establishes a novel paradigm for cognition-driven text understanding.

Abstract

Microblogging platforms generate massive amounts of short, noisy, and dispersed user content, making automatic keyphrase extraction (AKE) an important but challenging task. Prior studies have used eye-tracking signals to improve microblog-based AKE because such signals reflect readers' attention to salient words. However, eye tracking alone is limited by physiological, acquisition, and feature-decoding constraints. To address this issue, we investigate whether electroencephalogram (EEG) signals can complement eye-tracking signals for AKE. Using the ZuCo cognitive language processing corpus, we select 8 EEG features and 17 eye-tracking features and incorporate them into microblog-based AKE models. To reduce possible distortion of cognitive signals by model structures, we inject these features into the input of the soft-attention layer and the query vectors of the self-attention layer. We then evaluate different combinations of cognitive signals across AKE models. The results show that cognitive signals produced during reading consistently improve AKE performance, regardless of feature combinations and model architectures. EEG features bring the largest gains, while combining EEG and eye-tracking features yields performance between the two individual signal types, suggesting partial complementarity but also possible redundancy or noise. These findings indicate that EEG signals provide useful cognitive evidence for microblog-based AKE and that multimodal cognitive signals deserve further investigation.

Problem

• keyphrase extraction
• microblogs
• cognitive signals
• EEG
• eye-tracking

Innovation

• EEG signals
• eye-tracking
• keyphrase extraction
• cognitive signals
• attention mechanism