The DOI matches its Crossref record; 98 of the 98 references it cites were found in a registry or an index; 28 of the 74 sources its claims cite were checked for support.
Understanding Screenwriters' Practices, Attitudes, and Future Expectations in Human-AI Co-Creation
Open accessAbstract
With the rise of AI technologies and their growing influence in the screenwriting field, understanding the opportunities and concerns related to AI's role in screenwriting is essential for enhancing human-AI co-creation. Through semi-structured interviews with 23 screenwriters, we explored their creative practices, attitudes, and expectations in collaborating with AI for screenwriting. Based on participants' responses, we identified the key stages in which they commonly integrated AI, including story structure & plot development, screenplay text, goal & idea generation, and dialogue. Then, we examined how different attitudes toward AI integration influence screenwriters' practices across various workflow stages and their broader impact on the industry. Additionally, we categorized their expected assistance using four distinct roles of AI: actor, audience, expert, and executor. Our findings provide insights into AI's impact on screenwriting practices and offer suggestions on how AI can benefit the future of screenwriting.
Overview
CoChat Summary
TL;DR
This qualitative interview study examines how 23 screenwriters use, view, and envision AI in screenwriting workflows. It identifies current AI integration across key stages, mixed attitudes toward AI’s capabilities and industry impact, and four desired future roles for AI: actor, audience, expert, and executor.
Key findings
- 78% of participants (18/23) had used AI in screenwriting, most commonly in story structure & plot development, screenplay text, goal & idea generation, and dialogue; fewer used it in synopsis & outline.
- Satisfaction varied by stage: AI met basic needs in goal & idea and character tasks, but fewer were satisfied in story structure & plot (only 2 of 12 users), dialogue (none fully satisfied), and screenplay text (only P16 felt AI could optimize content).
- Positive attitudes centered on rapid generation to reduce trial-and-error costs (11 participants), efficient retrieval/summarization to expand knowledge boundaries (11 participants), and visual generation to inspire overlooked ideas (P11, P14, P16); negative attitudes cited high usage barriers, inaccuracy/uncontrollability, and lack of authentic experience/emotion perception (12 participants).
- Future expectations were categorized into four AI roles: “actor” for character simulation, “audience” for feedback, “expert” for professional guidance, and “executor” for task completion, mapped to different workflow stages.
Methods
- Semi-structured interviews with 23 screenwriters recruited via snowball sampling: 9 male, 14 female, aged 22–32 (average 25), with approximately four years of screenwriting experience on average and average self-reported AI proficiency of 3/5; 18 had used AI in screenwriting, 5 had not.
- Interviews used 27 open-ended questions, lasted approximately 80–100 minutes each, and were recorded and transcribed; data included about 1,992 minutes of audio, 117 pages of interview notes, and 558 pages of transcripts.
- Two authors conducted inductive thematic analysis following six stages of thematic analysis, without establishing inter-rater reliability, yielding three themes with nine sub-themes.
Limitations
- Stated: all participants were from China, which may introduce cultural and regional biases; professional backgrounds and years of screenwriting experience were self-reported and not directly correlated; AI proficiency varied and was not specifically compared across participants.
- Evident from the text: the sample is small and recruited through snowball sampling, limiting generalizability; the five participants who had not used AI were excluded from the task-allocation analysis in Section 4.3.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
16 Valid · 5 Not valid · 17 Not checked · 172 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“However, it provides limited insights into the nuanced relationship between screenwriters' diverse attitudes toward AI and its practical effects across various stages of their workflows.”
What the sources say
- Partly supportedcites [37] [37] Paolo Grigis and Antonella De Angeli. 2024. Playwriting with large language models: Perceived features, interaction strategies and outcomes. In Proceedings of the 2024 International Conference on Advanced Visual Interfaces . ACM, New York, NY, USA, Article 38, 9 pages. https://doi.org/10.1145/3656650.3656688 - sourceExperimental — accuracy not yet measured
Section 2.2.1 says that only a handful of user studies examine how professional writers perceive and use AI, and Section 5.3 notes that this study’s small group of playwrights reached a largely consensual evaluation. This supports a limited-insights claim, but the paper studies playwrights, not screenwriters, and does not specifically identify a gap concerning how diverse attitudes relate to practical effects across workflow stages. (LLM, conf=0.84)
- Not checked yetcites [46] [46] L Kavitha. 2023. Copyright challenges in the Artificial Intelligence revolution: Transforming the film industry from script to screen. Trinity Law Review 4, 1 (2023), 1-8. -
- Not checked — no full text of the sourcecites [24] [24] Pei-Sze Chow. 2020. Ghost in the (Hollywood) machine: Emergent applications of artificial intelligence in the film industry. European Journal of Media Studies 9, 1 (2020), 193-214. - source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“However, these studies focus solely on LLMs, neglecting advancements in AI-generated images and videos.”
What the sources say
- Supportedcites [37] [37] Paolo Grigis and Antonella De Angeli. 2024. Playwriting with large language models: Perceived features, interaction strategies and outcomes. In Proceedings of the 2024 International Conference on Advanced Visual Interfaces . ACM, New York, NY, USA, Article 38, 9 pages. https://doi.org/10.1145/3656650.3656688 - source
The Introduction states that this study evaluates commercial LLMs for playwriting, and the Case Study identifies the tools as three GPT-based writing systems. This supports the description of this paper’s scope as LLM-focused rather than a study of AI-generated images or videos. (LLM, conf=0.87)
- Supportedcites [70] [70] Piotr Mirowski, Kory W. Mathewson, Jaylen Pittman, and Richard Evans. 2023. Co-writing screenplays and theatre scripts with language models: Evaluation by industry professionals. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems . ACM, Article 355, 34 pages. https://doi.org/10. 1145/3544548.3581225 - source
The Introduction identifies Dramatron as an LLM-based co-writing tool, and Section 3.6 describes generating scripts and screenplays through text prompts and human edits. The paper’s stated study concerns script generation and evaluation, not AI-generated images or videos; the concept art and production photo mentioned elsewhere illustrate scripts rather than image or video generation. (LLM, conf=0.86)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“there remains limited understanding of how AI is applied across different stages of the screenwriting workflow.”
What the sources say
- Could not verifycites [13] [13] Daniel Kofi Brako and Anthony Kobina Mensah. 2023. Robots over humans? The place of artificial intelligence in the pedagogy of art direction in film education. Journal of Emerging Technologies 3, 2 (2023), 51-59. - sourceExperimental — accuracy not yet measured
The Methodology describes limited literature on AI in film art direction, not limited understanding of its use in screenwriting. The Introduction mentions an AI tool that analyzes scripts, but neither it nor the other passages addresses different stages of the screenwriting workflow (searched: screenwriting workflow stages; screenwriters and scriptwriting applications). (LLM, conf=0.77)
- Not checked — no full text of the sourcecites [73] [73] Aya Khalid Naji. 2024. Employing artificial intelligence techniques to make films. Al-Academy (2024), 171-180. - source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we identified participants' desired AI features in four roles: 'actor' for character simulation, 'audience' for feedback, 'expert' for professional advice, and 'executor' for completing tasks.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we identified the key stages in which they commonly integrated AI, including story structure & plot development, screenplay text, goal & idea generation, and dialogue.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
77 more claims
Create a free account to see all 210 claims and to verify the 14 references still open.
- Probably not a substantial claim. 98
- It may state two separate claims as one. 63
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“However, these accounts focus on isolated stages of use and therefore provide only snapshots of human-AI collaboration.”
From How Do Human Creators Embrace Human-AI Co-Creation? A Perspective on Human Agency of Screenwriters (2026) · cites this paper as [60]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“For example, the most relevant study by Tang et al. discusses AI integration in different tasks, such as ideation and character development, but does not reveal how these usage strategies were developed by screenwriters [60].”
From How Do Human Creators Embrace Human-AI Co-Creation? A Perspective on Human Agency of Screenwriters (2026) · cites this paper as [60]
The cited source says what the claim attributes to it.
In the citing paper
“Screenwriting is often a complex project involving multiple stages, such as ideation, outline drafting, scene development, and dialogue creation [60].”
From How Do Human Creators Embrace Human-AI Co-Creation? A Perspective on Human Agency of Screenwriters (2026) · cites this paper as [60]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 8.3 Facilitating Collaborative Training · p. 16
“Building on Kim et al.'s approach for short video producers [70]”
§ References · p. 18
“[70] Piotr Mirowski, Kory W. Mathewson, Jaylen Pittman, and Richard Evans. 2023. Co-writing screenplays and theatre scripts with language models: Evaluation by industry professionals.”
Citations
Cites
Using thematic analysis in psychology
Braun, V., & Clarke, V. (2006) · Qualitative Research in Psychology · doi:10.1191/1478088706qp063oa · Cited by 194,414
A Comprehensive Survey on Graph Neural Networks
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2978386 · Cited by 11,000 · cited 1×
“We propose tailored interaction design guidelines to effectively address the needs for emotional intelligence, role adaptability, and multithreaded dynamic outputs.”
Goodman, L. A. (1961) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177705148 · Cited by 3,606
A review on the attention mechanism of deep learning
Niu, Z., Zhong, G., & Yu, H. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.03.091 · Cited by 3,379 · cited 1×
“To ensure that AI models can generate contextually appropriate responses, it is possible to leverage reinforcement learning from human feedback (RLHF) techniques to train attention-based language models that can effectively capture the contextual information following humans’ approaches [74].”
Generative Agents: Interactive Simulacra of Human Behavior
Park, J. S., O'Brien, J., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023) · Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3586183.3606763 · Cited by 2,187 · cited 1×
“This capability could significantly enrich narrative development and improve the overall screenwriting experience.”
Generative Agents: Interactive Simulacra of Human Behavior
Park, J. S., O'Brien, J. C., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023) · arXiv · doi:10.48550/arxiv.2304.03442 · Cited by 2,173
World Medical Association (2025) · JAMA · doi:10.1001/jama.2024.21972 · Cited by 1,695
Film Form: Essays in Film Theory
Eisenstein, S. M., & Leyda, J. (1949) · Medical Entomology and Zoology · Cited by 848
Artificial intelligence in the creative industries: a review
Anantrasirichai, N., & Bull, D. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10039-7 · Cited by 793 · cited 1×
“Advancements in AI technology have significantly impacted various creative domains [3, 59], reshaping fields such as art [19] and design [58].”
Understanding and creating art with AI: Review and outlook
Cetinic, E., & She, J. (2022) · ACM Transactions on Multimedia Computing, Communications, and Applications · doi:10.1145/3475799 · Cited by 579
Research works printed but not linked: 8
- Alex Calderwood, Vivian Qiu, Katy Ilonka Gero, and Lydia B Chilton. 2020. How novelists use generative language models: An exploratory user study. In Proceedings of the IUI 2020 Workshop on Human-AI Co-Creation with Generative Models + User-Aware Conversational Agents.
- Brian Dunnigan. 2019. Screenwriting is filmmaking: The theory and practice of writing for the screen. The Crowood Press.
- David Howard and Edward Mabley. 1993. The tools of screenwriting: A writer’s guide to the craft and elements of a screenplay. Macmillan.
- L Kavitha. 2023. Copyright challenges in the Artificial Intelligence revolution: Transforming the film industry from script to screen. Trinity Law Review 4 1 (2023) 1–8.
- Michael Mateas. 2003. An experiment in building a fully-realized interactive drama. In Proceedings of the Game Developers Conference, Game Design Track, 2003.
- James R Meehan. 1977. TALE-SPIN, An interactive program that writes stories. In Proceedings of the International Joint Conferences on Artificial Intelligence , Vol. 77. 91–98.
- Adele Ramet. 2011. Creative writing. Hachette UK.
- KM Weiland. 2023. Creating character arcs: The masterful author’s guide to uniting story structure, plot and character development. MM Mukhi & Sons.
Cited by
The Impact of Artificial Intelligence on the Production and Editing of Audiovisual Content
Gavran, I. A., Honcharuk, S. M., Mykhalov, V. Y., Stepanenko, K. S., & Цімох, Н. І. (2025) · Preservation Digital Technology & Culture · doi:10.1515/pdtc-2025-0022 · Cited by 7
How Do Human Creators Embrace Human-AI Co-Creation? A Perspective on Human Agency of Screenwriters
Tang, Y., Zhou, J., Li, H., Xie, X., Ma, X., & Qu, H. (2026) · Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790300 · Cited by 5
“Tang et al. further illustrate how screen-writers assign different roles to AI and adopt distinct engagement modes during collaboration, offering a timely view of AI usage by screenwriters [60].”
InfluentialSelf-citationWriters Guild of America Strike 2023
Dwivedi, M. K., & Chhonkar, A. (2025) · Emerging Economies Cases Journal · doi:10.1177/25166042251397697 · Cited by 3
DuoDrama: Supporting Screenplay Refinement Through LLM-Assisted Human Reflection
Tang, Y., Chen, X., Li, H., Xie, X., Ma, X., & Qu, H. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790568 · Cited by 5
“In the refinement stage, however, screenwriters do not only seek AI-generated content but also expect AI to provide feedback that supports their reflection on scene logic, character motivation, and authorial intent [60].”
InfluentialSelf-citationConstella: Supporting Storywriters’ Interconnected Character Creation through LLM-Based Multi-Agents
Park, S., Park, S., & Lim, Y.-K. (2026) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3796234 · Cited by 7
Metadata
- Authors
- Tang, Y., Li, H., Lan, M., Ma, X., & Qu, H.
- Affiliations
- Hong Kong University of Science and Technology (HK)
- Microsoft Research Asia (China) (CN)
- Central Academy of Fine Arts (CN)
- Venue
- Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2025-04-25
- Pages
- 1-18
- OpenAlex
- W4409747502
- Cited by
- 18
- References
- 83
- Citations by year
- 2026: 11 · 2025: 7
- FWCI
- 143.09
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- CHI Conference on Human Factors in Computing Systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Social Sciences › Arts and Humanities › Visual Arts and Performing Arts › Artistic and Creative Research
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Digital Media and Visual Art
- Social Sciences › Arts and Humanities › Visual Arts and Performing Arts › Art, Technology, and Culture
- Keywords
- screenwriting, human-AI co-creation, dialogue generation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-30, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-30 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Understanding Screenwriters' Practices, Attitudes, and Future Expectations in Human-AI Co-Creation. https://app.cochat.ai/papers/10.1145/3706598.3714120
- The paper
- Tang, Y., Li, H., Lan, M., Ma, X., & Qu, H. (2025). Understanding Screenwriters' Practices, Attitudes, and Future Expectations in Human-AI Co-Creation. Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3706598.3714120
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.