Linguistic Markers of Inherently False AI Communication and Intentionally False Human Communication: Evidence from Hotel Reviews

Markowitz, David M.; Hancock, Jeffrey T.; Bailenson, Jeremy N.

doi:10.31234/osf.io/mnyz8

Cited by 2 publications

(7 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The changes to the prompts were derived from past work that showed how minor changes to the self-report design, such as adding contextual information or changing the response scale, can elicit di erent response patterns (Schwarz, 1999). Our findings demonstrate, in line with recent works on the e ect of prompting (Fujita et al, 2022;Gan & Mori, 2023;Lu et al, 2021;Markowitz, 2023;, that minor changes in prompts lead to significant di erences in outputs. For example, adding a study Agreeableness (d = ≠0.14; p < .001; 95%CI [-0.18, -0.10]).…”

Section: Reproducibility Matterssupporting

confidence: 84%

“…Liu et al, 2023;Romera-Paredes & Torr, 2015), for psychological text analysis, presumably due to their ease of use and accessibility. For example, Markowitz (2023), Rathje et al (2023), andZhu et al (2023) reported high performance of ChatGPT as an automated text analysis tool, such as for sentiment analysis, o ensive language, thinking style, or emotion detection. Rathje et al (2023) further concluded that LLMs constitute a viable all-purpose method for psychological text analysis, arguably more convenient than small(er) language models and traditional techniques in NLP, due to their ability to handle diverse tasks within a single model PERILS AND OPPORTUNITIES OF LLMS 15 without needing task-specific adjustments, and their user-friendly design that minimizes the need for complex coding, making them more accessible to psychologists and potentially encouraging broader research engagement.…”

Section: Llms Are Not An All-purpose Methodsmentioning

confidence: 99%

“…Moreover, prompting also introduces significant challenges to reproducibility in psychological research, because prompts can be constructed in numerous ways. Past work has shown that slight alterations and modifications in phrasing, context, or order can lead to substantially di erent responses (Fujita et al, 2022;Gan & Mori, 2023;Lu et al, 2021;Markowitz, 2023;Mishra et al, 2023;.…”

Section: Reproducibility Mattersmentioning

confidence: 99%

See 2 more Smart Citations

Perils and Opportunities in Using Large Language Models in Psychological Research

Abdurahman,

Atari,

Karimi-Malekabadi

et al. 2023

Preprint

View full text Add to dashboard Cite

The emergence of large language models (LLMs) has sparked considerable interest in their potential application in psychological research, either as a human-like entity used as a model for the human psyche or as a general text-analysis tool. However, carelessly using LLMs in psychological studies, a trend we rhetorically refer to as “GPTology,” can have negative consequences, especially given the convenient access to models such as ChatGPT. We elucidate the promises, limitations, and ethical considerations of using LLMs in psychological research. First, LLM-based research should pay attention to the substantial psychological diversity around the globe, as well as demographic diversity within populations. Second, while LLMs are convenient tools, we caution against treating them as a one-size-fits-all method for psychological text analysis. Third, LLM-based psychological research needs to develop methods and standards to compensate for LLMs’ opaque black-box nature to facilitate reproducibility, transparency, and robust inference from AI-generated data. While acknowledging the prospects offered by LLMs for easy task automation (e.g., text annotation) and to expand our understanding of human psychology (e.g., by contrasting human and machine psychology), we make a case for diversifying human samples and expanding psychology’s methodological toolbox to achieve a truly inclusive and generalizable science, rather than homogenizing samples and methods through over-reliance on LLMs.

show abstract

Section: Reproducibility Matterssupporting

confidence: 84%

Section: Llms Are Not An All-purpose Methodsmentioning

confidence: 99%

Section: Reproducibility Mattersmentioning

confidence: 99%

See 1 more Smart Citation

Perils and Opportunities in Using Large Language Models in Psychological Research

Abdurahman,

Atari,

Karimi-Malekabadi

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Liu et al, 2023;Romera-Paredes & Torr, 2015), for psychological text analysis, presumably due to their ease of use and accessibility. For example, Markowitz (2023), Rathje et al (2023), andZhu et al (2023) reported high performance of ChatGPT as an automated text analysis tool, such as for sentiment analysis, offensive language, thinking style, or emotion detection. Rathje et al (2023) further concluded that LLMs constitute a viable all-purpose method for psychological text analysis, arguably more convenient than small(er) language models and traditional techniques in NLP, due to their ability to handle diverse tasks within a single model PERILS AND OPPORTUNITIES OF LLMS 15 without needing task-specific adjustments, and their user-friendly design that minimizes the need for complex coding, making them more accessible to psychologists and potentially encouraging broader research engagement.…”

Section: Llms Are Not An All-purpose Methodsmentioning

confidence: 99%

“…Moreover, prompting also introduces significant challenges to reproducibility in psychological research, because prompts can be constructed in numerous ways. Past work has shown that slight alterations and modifications in phrasing, context, or order can lead to substantially different responses (Fujita et al, 2022;Gan & Mori, 2023;Lu et al, 2021;Markowitz, 2023;Mishra et al, 2023;.…”

Section: Reproducibility Mattersmentioning

confidence: 99%

Perils and Opportunities in Using Large Language Models in Psychological Research

Abdurahman,

Atari,

Karimi-Malekabadi

et al. 2023

Preprint

View full text Add to dashboard Cite

The emergence of large language models (LLMs) has sparked considerable interest in their potential application in psychological research, either as a human-like entity used as a model for the human psyche or as a general text-analysis tool. However, carelessly using LLMs in psychological studies, a trend we rhetorically refer to as ``GPTology,'' can have negative consequences, especially given the convenient access to models such as ChatGPT. We elucidate the promises, limitations, and ethical considerations of using LLMs in psychological research. First, LLM-based research should pay attention to the substantial psychological diversity around the globe, as well as demographic diversity within populations. Second, while LLMs are convenient tools, we caution against treating them as a one-size-fits-all method for psychological text analysis. Third, LLM-based psychological research needs to develop methods and standards to compensate for LLMs' opaque black-box nature to facilitate reproducibility, transparency, and robust inference from AI-generated data.While acknowledging the prospects offered by LLMs for easy task automation (e.g., text annotation) and to expand our understanding of human psychology (e.g., by contrasting human and machine psychology), we make a case for diversifying human samples and expanding psychology's methodological toolbox to achieve a truly inclusive and generalizable science, rather than homogenizing samples and methods through over-reliance on LLMs.

show abstract

Linguistic Markers of Inherently False AI Communication and Intentionally False Human Communication: Evidence from Hotel Reviews

Cited by 2 publications

References 39 publications

Perils and Opportunities in Using Large Language Models in Psychological Research

Perils and Opportunities in Using Large Language Models in Psychological Research

Perils and Opportunities in Using Large Language Models in Psychological Research

Contact Info

Product

Resources

About