Do Artificial Intelligence Chatbots Have a Writing Style? An Investigation into the Stylistic Features of ChatGPT-4

M. AlAfnan, Siti Fatimah MohdZuki
{"title":"Do Artificial Intelligence Chatbots Have a Writing Style? An Investigation into the Stylistic Features of ChatGPT-4","authors":"M. AlAfnan, Siti Fatimah MohdZuki","doi":"10.37965/jait.2023.0267","DOIUrl":null,"url":null,"abstract":"Even though Turnitin generates AI (Artificial Intelligence) writing detection reports, these AI reports shall not be used for punitive purposes as Turnitin AI reports accuracy is way below the 98% claimed by Turnitin, as revealed in this study. To assist professors, teachers, and content evaluation stakeholders in their strive to identify AI-generated material, this study examines the stylistic features of case study, business correspondence, and academic writing ChatGPT-4 generated responses by exploring sentence length, paragraph structure, word choice, mood, tense, voice, pronouns, keywords density, lexical density, lexical diversity, and reading ease. The study revealed that ChatGPT-4 case study generated responses are produced in paragraphs of 2 to 3 sentences of 16 to 18 words each. The sentences are mainly formed in imperative mood. The use of the second-person pronoun ‘you’ and the second-person possessive determiner ‘your’ is prevalent. Keywords and lexical density are relatively low, lexical diversity is average, and the reading ease is relatively high. The study also found that ChatGPT-4 business correspondence responses are generated in paragraphs of 2 to 3 sentences of 16 to 20 words each. The sentences are mainly generated in declarative mood thru simple present tense in active voice using third-person singular pronouns. Technical words and abbreviations are used without outlining what they stand for. The keywords density, lexical density, and lexical diversity are high and the reading ease is low. The study also revealed that ChatGPT-4 academic writing generated responses are provided in paragraphs of 3 to 4 sentences of 16 to 19 words each. The sentences are mainly generated in declarative mood using active voice, agentless passive in times, with diverse present tenses. Keywords and lexical densities are high and the lexical diversity is low, which makes the reading ease average difficulty, except for the undefined abbreviations. Noticeably, ChatGPT-4 supports the transgender movement by intentionally using the third-person plural pronoun ‘they’ to refer to a singular.","PeriodicalId":70996,"journal":{"name":"人工智能技术学报(英文)","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"人工智能技术学报(英文)","FirstCategoryId":"1093","ListUrlMain":"https://doi.org/10.37965/jait.2023.0267","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

Abstract

Even though Turnitin generates AI (Artificial Intelligence) writing detection reports, these AI reports shall not be used for punitive purposes as Turnitin AI reports accuracy is way below the 98% claimed by Turnitin, as revealed in this study. To assist professors, teachers, and content evaluation stakeholders in their strive to identify AI-generated material, this study examines the stylistic features of case study, business correspondence, and academic writing ChatGPT-4 generated responses by exploring sentence length, paragraph structure, word choice, mood, tense, voice, pronouns, keywords density, lexical density, lexical diversity, and reading ease. The study revealed that ChatGPT-4 case study generated responses are produced in paragraphs of 2 to 3 sentences of 16 to 18 words each. The sentences are mainly formed in imperative mood. The use of the second-person pronoun ‘you’ and the second-person possessive determiner ‘your’ is prevalent. Keywords and lexical density are relatively low, lexical diversity is average, and the reading ease is relatively high. The study also found that ChatGPT-4 business correspondence responses are generated in paragraphs of 2 to 3 sentences of 16 to 20 words each. The sentences are mainly generated in declarative mood thru simple present tense in active voice using third-person singular pronouns. Technical words and abbreviations are used without outlining what they stand for. The keywords density, lexical density, and lexical diversity are high and the reading ease is low. The study also revealed that ChatGPT-4 academic writing generated responses are provided in paragraphs of 3 to 4 sentences of 16 to 19 words each. The sentences are mainly generated in declarative mood using active voice, agentless passive in times, with diverse present tenses. Keywords and lexical densities are high and the lexical diversity is low, which makes the reading ease average difficulty, except for the undefined abbreviations. Noticeably, ChatGPT-4 supports the transgender movement by intentionally using the third-person plural pronoun ‘they’ to refer to a singular.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
人工智能聊天机器人有写作风格吗?ChatGPT-4的文体特征研究
尽管Turnitin生成AI(人工智能)书写检测报告,但这些AI报告不应用于惩罚目的,因为Turnitin AI报告的准确率远低于Turnitin声称的98%,正如本研究所揭示的那样。为了帮助教授、教师和内容评估利益相关者努力识别人工智能生成的材料,本研究通过探索句子长度、段落结构、单词选择、语气、时态、声音、代词、关键词密度、词汇密度、词汇多样性,考察了案例研究、商务信函和学术写作ChatGPT-4生成的回应的风格特征,阅读方便。研究表明,ChatGPT-4案例研究产生的回答是在2到3个句子的段落中产生的,每个句子16到18个单词。这些句子主要是在祈使语气中形成的。第二人称代词“you”和第二人称所有格限定词“your”的使用很普遍。关键词和词汇密度相对较低,词汇多样性一般,阅读难度相对较高。研究还发现,ChatGPT-4商务信函的回复是在2到3个句子的段落中生成的,每个句子16到20个单词。这些句子主要是通过使用第三人称单数代词的主动语态中的简单现在时在陈述语气中产生的。使用技术术语和缩写时没有概述它们的含义。关键词密度、词汇密度和词汇多样性较高,阅读难度较低。该研究还显示,ChatGPT-4学术写作产生的回答以3至4段的句子提供,每段16至19个单词。这些句子主要是在陈述语气中产生的,使用主动语态,在时间上使用无主体被动语态,具有不同的现在时态。关键词和词汇密度较高,词汇多样性较低,除未定义的缩写外,阅读难度一般。值得注意的是,ChatGPT-4有意使用第三人称复数代词“they”来指代单数,从而支持跨性别运动。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
8.70
自引率
0.00%
发文量
0
期刊最新文献
Detection of Streaks in Astronomical Images Using Machine Learning An Optimal BDCNN ML Architecture for Car Make Model Prediction A Bio-Inspired Method For Breast Histopathology Image Classification Using Transfer Learning Convolutional Neural Networks for Automated Diagnosis of Diabetic Retinopathy in Fundus Images Automated Staging and Grading for Retinopathy of Prematurity on Indian Database
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1