When Do We Talk to AI? A User-Centric Analysis of ChatGPT Interaction Patterns

Avshalom Elmalech; Ronyt Gomez; Israel Klein

doi:10.1007/978-981-95-4861-3_13

When Do We Talk to AI? A User-Centric Analysis of ChatGPT Interaction Patterns

Avshalom Elmalech
, Ronyt Gomez
, Israel Klein

Ariel University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

As generative AI systems like ChatGPT become integrated into daily routines, understanding how different users engage with these tools over time is essential for designing future information services. This paper presents an empirical user study examining ChatGPT usage patterns across a diverse set of 38 participants. Using exported chat histories, we analyze over 82,000 prompts spanning up to 21 months per participant. Our findings reveal distinct interaction behaviors tied to age, gender, and time of day. Notably, older users exhibit stronger work-week patterns in usage, while women show higher activity at night. These results highlight the roles generative AI plays in users’ lives, extending beyond productivity into moments of reflection, support, and multitasking.

Original language	English
Title of host publication	Intelligence and Equity
Subtitle of host publication	Shaping the Future of Knowledge - 27th International Conference on Asian Digital Libraries, ICADL 2025, Proceedings
Editors	Sanghee Oh, Antoine Doucet, Marut Buranarach, Iyra Buenrostro-Cabbab, Benedict Salazar Olgado, Yuenan Liu
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	143-149
Number of pages	7
ISBN (Print)	9789819548606
DOIs	https://doi.org/10.1007/978-981-95-4861-3_13
State	Published - 2026
Event	27th International Conference on Asia-Pacific Digital Libraries, ICADL 2025 - Metro Manila, Philippines Duration: 3 Dec 2025 → 5 Dec 2025

Publication series

Name	Lecture Notes in Computer Science
Volume	16242 LNCS
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	27th International Conference on Asia-Pacific Digital Libraries, ICADL 2025
Country/Territory	Philippines
City	Metro Manila
Period	3/12/25 → 5/12/25

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.

Keywords

Generative AI
Human–I interaction
User behavior analytics

Access to Document

10.1007/978-981-95-4861-3_13

Cite this

Elmalech, A., Gomez, R., & Klein, I. (2026). When Do We Talk to AI? A User-Centric Analysis of ChatGPT Interaction Patterns. In S. Oh, A. Doucet, M. Buranarach, I. Buenrostro-Cabbab, B. S. Olgado, & Y. Liu (Eds.), Intelligence and Equity: Shaping the Future of Knowledge - 27th International Conference on Asian Digital Libraries, ICADL 2025, Proceedings (pp. 143-149). (Lecture Notes in Computer Science; Vol. 16242 LNCS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-95-4861-3_13

Elmalech, Avshalom ; Gomez, Ronyt ; Klein, Israel. / When Do We Talk to AI? A User-Centric Analysis of ChatGPT Interaction Patterns. Intelligence and Equity: Shaping the Future of Knowledge - 27th International Conference on Asian Digital Libraries, ICADL 2025, Proceedings. editor / Sanghee Oh ; Antoine Doucet ; Marut Buranarach ; Iyra Buenrostro-Cabbab ; Benedict Salazar Olgado ; Yuenan Liu. Springer Science and Business Media Deutschland GmbH, 2026. pp. 143-149 (Lecture Notes in Computer Science).

@inproceedings{c3dce2ff0be441ff8fe13314b8be3188,

title = "When Do We Talk to AI? A User-Centric Analysis of ChatGPT Interaction Patterns",

abstract = "As generative AI systems like ChatGPT become integrated into daily routines, understanding how different users engage with these tools over time is essential for designing future information services. This paper presents an empirical user study examining ChatGPT usage patterns across a diverse set of 38 participants. Using exported chat histories, we analyze over 82,000 prompts spanning up to 21 months per participant. Our findings reveal distinct interaction behaviors tied to age, gender, and time of day. Notably, older users exhibit stronger work-week patterns in usage, while women show higher activity at night. These results highlight the roles generative AI plays in users{\textquoteright} lives, extending beyond productivity into moments of reflection, support, and multitasking.",

keywords = "Generative AI, Human–I interaction, User behavior analytics",

author = "Avshalom Elmalech and Ronyt Gomez and Israel Klein",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.; 27th International Conference on Asia-Pacific Digital Libraries, ICADL 2025 ; Conference date: 03-12-2025 Through 05-12-2025",

year = "2026",

doi = "10.1007/978-981-95-4861-3\_13",

language = "אנגלית",

isbn = "9789819548606",

series = "Lecture Notes in Computer Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "143--149",

editor = "Sanghee Oh and Antoine Doucet and Marut Buranarach and Iyra Buenrostro-Cabbab and Olgado, \{Benedict Salazar\} and Yuenan Liu",

booktitle = "Intelligence and Equity",

address = "גרמניה",

}

Elmalech, A, Gomez, R & Klein, I 2026, When Do We Talk to AI? A User-Centric Analysis of ChatGPT Interaction Patterns. in S Oh, A Doucet, M Buranarach, I Buenrostro-Cabbab, BS Olgado & Y Liu (eds), Intelligence and Equity: Shaping the Future of Knowledge - 27th International Conference on Asian Digital Libraries, ICADL 2025, Proceedings. Lecture Notes in Computer Science, vol. 16242 LNCS, Springer Science and Business Media Deutschland GmbH, pp. 143-149, 27th International Conference on Asia-Pacific Digital Libraries, ICADL 2025, Metro Manila, Philippines, 3/12/25. https://doi.org/10.1007/978-981-95-4861-3_13

When Do We Talk to AI? A User-Centric Analysis of ChatGPT Interaction Patterns. / Elmalech, Avshalom; Gomez, Ronyt; Klein, Israel.
Intelligence and Equity: Shaping the Future of Knowledge - 27th International Conference on Asian Digital Libraries, ICADL 2025, Proceedings. ed. / Sanghee Oh; Antoine Doucet; Marut Buranarach; Iyra Buenrostro-Cabbab; Benedict Salazar Olgado; Yuenan Liu. Springer Science and Business Media Deutschland GmbH, 2026. p. 143-149 (Lecture Notes in Computer Science; Vol. 16242 LNCS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - When Do We Talk to AI? A User-Centric Analysis of ChatGPT Interaction Patterns

AU - Elmalech, Avshalom

AU - Gomez, Ronyt

AU - Klein, Israel

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.

PY - 2026

Y1 - 2026

N2 - As generative AI systems like ChatGPT become integrated into daily routines, understanding how different users engage with these tools over time is essential for designing future information services. This paper presents an empirical user study examining ChatGPT usage patterns across a diverse set of 38 participants. Using exported chat histories, we analyze over 82,000 prompts spanning up to 21 months per participant. Our findings reveal distinct interaction behaviors tied to age, gender, and time of day. Notably, older users exhibit stronger work-week patterns in usage, while women show higher activity at night. These results highlight the roles generative AI plays in users’ lives, extending beyond productivity into moments of reflection, support, and multitasking.

AB - As generative AI systems like ChatGPT become integrated into daily routines, understanding how different users engage with these tools over time is essential for designing future information services. This paper presents an empirical user study examining ChatGPT usage patterns across a diverse set of 38 participants. Using exported chat histories, we analyze over 82,000 prompts spanning up to 21 months per participant. Our findings reveal distinct interaction behaviors tied to age, gender, and time of day. Notably, older users exhibit stronger work-week patterns in usage, while women show higher activity at night. These results highlight the roles generative AI plays in users’ lives, extending beyond productivity into moments of reflection, support, and multitasking.

KW - Generative AI

KW - Human–I interaction

KW - User behavior analytics

UR - https://www.scopus.com/pages/publications/105024562862

U2 - 10.1007/978-981-95-4861-3_13

DO - 10.1007/978-981-95-4861-3_13

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:105024562862

SN - 9789819548606

T3 - Lecture Notes in Computer Science

SP - 143

EP - 149

BT - Intelligence and Equity

A2 - Oh, Sanghee

A2 - Doucet, Antoine

A2 - Buranarach, Marut

A2 - Buenrostro-Cabbab, Iyra

A2 - Olgado, Benedict Salazar

A2 - Liu, Yuenan

PB - Springer Science and Business Media Deutschland GmbH

T2 - 27th International Conference on Asia-Pacific Digital Libraries, ICADL 2025

Y2 - 3 December 2025 through 5 December 2025

ER -

Elmalech A, Gomez R, Klein I. When Do We Talk to AI? A User-Centric Analysis of ChatGPT Interaction Patterns. In Oh S, Doucet A, Buranarach M, Buenrostro-Cabbab I, Olgado BS, Liu Y, editors, Intelligence and Equity: Shaping the Future of Knowledge - 27th International Conference on Asian Digital Libraries, ICADL 2025, Proceedings. Springer Science and Business Media Deutschland GmbH. 2026. p. 143-149. (Lecture Notes in Computer Science). doi: 10.1007/978-981-95-4861-3_13