Utilizing Cognitive Signals Generated during Human Reading to Enhance Keyphrase Extraction from Microblogs
Quick Answer
This study demonstrates that integrating EEG signals with eye-tracking data significantly enhances automatic keyphrase extraction (AKE) from microblogs.
Quick Take
This study demonstrates that integrating EEG signals with eye-tracking data significantly enhances automatic keyphrase extraction (AKE) from microblogs. Using the ZuCo corpus, the research shows that EEG features provide the most substantial performance improvements, indicating their potential as valuable cognitive evidence for AKE models.
Key Points
- EEG signals consistently improve AKE performance across various model architectures.
- Combining EEG and eye-tracking features yields intermediate performance, indicating partial complementarity.
- Eight EEG features and 17 eye-tracking features were evaluated for AKE enhancement.
- Cognitive signals during reading are crucial for effective keyphrase extraction from noisy microblog data.
- Further investigation into multimodal cognitive signals is warranted based on these findings.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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.
| Subjects: | Computation and Language (cs.CL); Digital Libraries (cs.DL); Human-Computer Interaction (cs.HC); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2606.26485 [cs.CL] |
| (or arXiv:2606.26485v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2606.26485 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | IPM, 2024 |
| Related DOI: | https://doi.org/10.1016/j.ipm.2023.103614
DOI(s) linking to related resources |
Submission history
From: Chengzhi Zhang [view email]
[v1]
Thu, 25 Jun 2026 00:43:12 UTC (1,696 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Quantifying Prior Dominance in Systems
The study introduces the Normalized Context Utilization (NCU) metric to evaluate Retrieval-Augmented Generation (RAG) systems, revealing that Small Language Models (SLMs) outperform larger models in factual extraction. The findings indicate that traditional scaling laws yield diminishing returns, with a commercial API frequently failing against adversarial evidence due to systemic confidence collapse.