{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:44:09Z","timestamp":1782848649760,"version":"3.54.5"},"reference-count":32,"publisher":"Association for Computing Machinery (ACM)","issue":"FSE","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Softw. Eng."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>Emotional requirements (ERs)---how users should feel and which emotional harms a system must avoid---often determine whether people adopt and keep using software, especially in sensitive domains. Yet, eliciting ERs via interviews, workshops, and focus groups is costly and hard to scale or repeat. We study whether simulated focus groups, moderated discussions among user personas generated and played by large language models (LLMs), can augment early ER elicitation. Across three domains (mental\u2011health journaling, personal finance, and fitness), we compare one\u2011shot and iterative single\u2011model pipelines with iterative pipelines that use two or three different LLMs, and we benchmark against two human baselines: a human focus group and Emotional Goal Modeling (EGM). Multi\u2011LLM pipelines generate more diverse personas and increase the share of AI\u2011only ERs (not seen in our human baselines) that source\u2011blinded raters judge relevant by 14.7 percentage points compared to an iterative single\u2011model workflow; same\u2011model controls suggest this gain is not solely due to provider differences. Compared to human methods, simulations contribute more innovative requirements, EGM contributes clearer and more feasible ones, and human focus groups provide more natural phrasing. Overall, the results support an augmentation\u2011oriented workflow: use multi\u2011LLM simulation to broaden candidate ERs, structured modeling to organize them, and human engagement to ground decisions.<\/jats:p>","DOI":"10.1145\/3808098","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:06:14Z","timestamp":1782839174000},"page":"2027-2048","source":"Crossref","is-referenced-by-count":0,"title":["Multi-LLM Persona Generation for Virtual Focus Groups in Software Engineering: A Controlled, Multi-domain Study of Emotional Requirements Elicitation"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0001-8570-1636","authenticated-orcid":false,"given":"Guangrui","family":"Fan","sequence":"first","affiliation":[{"name":"Taiyuan University of Science and Technology, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0002-4702-8070","authenticated-orcid":false,"given":"Dandan","family":"Liu","sequence":"additional","affiliation":[{"name":"Universiti Malaya, Kuala Lumpur, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-9530-694X","authenticated-orcid":false,"given":"Lihu","family":"Pan","sequence":"additional","affiliation":[{"name":"Taiyuan University of Science and Technology, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-7767-7413","authenticated-orcid":false,"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Taiyuan University of Science and Technology, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-9189-7834","authenticated-orcid":false,"given":"Qian","family":"Guo","sequence":"additional","affiliation":[{"name":"Taiyuan University of Science and Technology, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1782"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10515-023-00407-8"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.47289\/AIEJ20240122"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/wsese66602.2025.00015"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.2196\/64447"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","unstructured":"Ricardo Colomo Palacios Cristina Casado-Lumbreras Pedro Soto-Acosta and \u00c1ngel Garc\u00eda Crespo. 2011. Using the affect grid to measure emotions in software requirements engineering. (2011). doi:10.3217\/jucs-017-09-1281 10.3217\/jucs-017-09-1281","DOI":"10.3217\/jucs-017-09-1281"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.34068\/joe.63.01.16"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.4018\/ijpop"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.2196\/59641"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2025.107697"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/re59067.2024.00044"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.24018\/ejeng"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1177\/16094069251322346"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0290773"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","unstructured":"Javed Ali Khan Shamaila Qayyum and Hafsa Shareef Dar. 2025. Large Language Model for Requirements Engineering: A Systematic Literature Review. (2025). doi:10.21203\/rs.3.rs-5589929\/v1 10.21203\/rs.3.rs-5589929\/v1","DOI":"10.21203\/rs.3.rs-5589929\/v1"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000198"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/RE63999.2025.00031"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/itl2.70016"},{"key":"e_1_2_1_19_1","volume-title":"Haijun Xia, and Yun Huang.","author":"Liu Yiren","year":"2024","unstructured":"Yiren Liu, Pranav Sharma, Mehul Jitendra Oswal, Haijun Xia, and Yun Huang. 2024. Personaflow: Boosting research ideation with llm-simulated expert personas. arXiv preprint arXiv:2409.12538 (2024)."},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3724389"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/tse"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.3390\/fi16060180"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2015.03.044"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1177\/10506519241239927"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2901739.2903505"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"e_1_2_1_27_1","volume-title":"Casey Randazzo, David Mimno, and Sarita Schoenebeck.","author":"Schroeder Hope","year":"2024","unstructured":"Hope Schroeder, Marianne Aubin Le Qu\u00e9r\u00e9, Casey Randazzo, David Mimno, and Sarita Schoenebeck. 2024. Large language models in qualitative research: Can we do the data justice? arXiv preprint arXiv:2410.07362 (2024)."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1177\/00491241251339188"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00766-017-0273-y"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.277"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1101\/2025.04.10.647852"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3652988"}],"container-title":["Proceedings of the ACM on Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/pdf\/10.1145\/3808098","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:49:24Z","timestamp":1782845364000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/10.1145\/3808098"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":32,"journal-issue":{"issue":"FSE","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3808098"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/3808098","relation":{},"ISSN":["2994-970X"],"issn-type":[{"value":"2994-970X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]}}}