Metraipolis › archive › dc_7161fdeeb5aa

ClickSight: An LLM Framework for Interpreting Student Clickstreams Through Learning Strategies — arXiv:2611.02021

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.02021
License (as archived): CC0-1.0
Archived: 2026-11-03T18:13:48.659Z
SHA-256 of the archived text: 9ea97717acf70d52a115b6f47c14ffa0111aadd16cdeb33719e2d00981dcd7ee
Stable URL of this page: https://metraipolis.com/documento/dc_7161fdeeb5aa

How to cite

ClickSight: An LLM Framework for Interpreting Student Clickstreams Through Learning Strategies — arXiv:2611.02021 — arXiv (en), https://arxiv.org/abs/2611.02021 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7161fdeeb5aa (Metraipolis archive dc_7161fdeeb5aa, sha256 9ea97717acf70d52a115b6f47c14ffa0111aadd16cdeb33719e2d00981dcd7ee)

BibTeX

@misc{dc7161fdeeb5aa,
  title = {ClickSight: An LLM Framework for Interpreting Student Clickstreams Through Learning Strategies — arXiv:2611.02021},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02021},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7161fdeeb5aa; sha256 9ea97717acf70d52a115b6f47c14ffa0111aadd16cdeb33719e2d00981dcd7ee},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02021. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Digital learning environments produce rich clickstream data that can reveal how students approach learning tasks, yet interpreting these fine-grained traces often requires substantial expert effort. We introduce ClickSight, a framework for interpreting student clickstreams through learning strategies defined in the literature. Given a student clickstream and a predefined set of learning strategies, ClickSight uses a staged LLM-based pipeline to identify strategy-relevant evidence, assess adherence to each strategy, and generate an evidence-grounded interpretation of the student's behavior. We evaluate ClickSight across two learning environments, 365 students, and 12 model backbones using an expert-grounded quality rubric and an LLM judge calibrated with human-expert ratings. Our results show that ClickSight can generate high-quality strategy-based interpretations across different models and environments, with reasoning models performing more consistently than instruction-tuned counterparts. We further find that providing external clickstream-extracted guidance can improve interpretation quality for strategies that require precise quantitative information from the trace. By connecting fine-grained clickstreams with theoretically defined learning strategies and preserving the evidence underlying each judgment, ClickSight provides a flexible approach for studying student behavior in digital learning environments.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2611.02021 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T18:09:53.367Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).