Behind India's ChatGPT Conversations: A Retrospective Analysis of 238 Unedited User Prompts
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915497734307840 |
|---|---|
| author | Khona, Kalyani |
| author_facet | Khona, Kalyani |
| contents | Understanding how users authentically interact with Large Language Models (LLMs) remains a significant challenge in human-computer interaction research. Most existing studies rely on self-reported usage patterns or controlled experimental conditions, potentially missing genuine behavioral adaptations. This study presents a behavioral analysis of the use of English-speaking urban professional ChatGPT in India based on 238 authentic, unedited user prompts from 40 participants in 15+ Indian cities, collected using retrospective survey methodology in August 2025. Using authentic retrospective prompt collection via anonymous social media survey to minimize real-time observer effects, we analyzed genuine usage patterns. Key findings include: (1) 85\% daily usage rate (34/40 users) indicating mature adoption beyond experimental use, (2) evidence of cross-domain integration spanning professional, personal, health and creative contexts among the majority of users, (3) 42.5\% (17/40) primarily use ChatGPT for professional workflows with evidence of real-time problem solving integration, and (4) cultural context navigation strategies with users incorporating Indian cultural specifications in their prompts. Users develop sophisticated adaptation techniques and the formation of advisory relationships for personal guidance. The study reveals the progression from experimental to essential workflow dependency, with users treating ChatGPT as an integrated life assistant rather than a specialized tool. However, the findings are limited to urban professionals in English recruited through social media networks and require a larger demographic validation. This work contributes a novel methodology to capture authentic AI usage patterns and provides evidence-based insights into cultural adaptation strategies among this specific demographic of users. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13337 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Behind India's ChatGPT Conversations: A Retrospective Analysis of 238 Unedited User Prompts Khona, Kalyani Computers and Society H.5.2; K.4.3; J.4 Understanding how users authentically interact with Large Language Models (LLMs) remains a significant challenge in human-computer interaction research. Most existing studies rely on self-reported usage patterns or controlled experimental conditions, potentially missing genuine behavioral adaptations. This study presents a behavioral analysis of the use of English-speaking urban professional ChatGPT in India based on 238 authentic, unedited user prompts from 40 participants in 15+ Indian cities, collected using retrospective survey methodology in August 2025. Using authentic retrospective prompt collection via anonymous social media survey to minimize real-time observer effects, we analyzed genuine usage patterns. Key findings include: (1) 85\% daily usage rate (34/40 users) indicating mature adoption beyond experimental use, (2) evidence of cross-domain integration spanning professional, personal, health and creative contexts among the majority of users, (3) 42.5\% (17/40) primarily use ChatGPT for professional workflows with evidence of real-time problem solving integration, and (4) cultural context navigation strategies with users incorporating Indian cultural specifications in their prompts. Users develop sophisticated adaptation techniques and the formation of advisory relationships for personal guidance. The study reveals the progression from experimental to essential workflow dependency, with users treating ChatGPT as an integrated life assistant rather than a specialized tool. However, the findings are limited to urban professionals in English recruited through social media networks and require a larger demographic validation. This work contributes a novel methodology to capture authentic AI usage patterns and provides evidence-based insights into cultural adaptation strategies among this specific demographic of users. |
| title | Behind India's ChatGPT Conversations: A Retrospective Analysis of 238 Unedited User Prompts |
| topic | Computers and Society H.5.2; K.4.3; J.4 |
| url | https://arxiv.org/abs/2509.13337 |