Comparisons of Quality, Correctness, and Similarity Between ChatGPT-Generated and Human-Written Abstracts for Basic Research: Cross-Sectional Study
ChatGPT may act as a research assistant to help organize the direction of thinking and summarize research findings. However, few studies have examined the quality, similarity (abstracts being similar to the original one), and accuracy of the abstracts generated by ChatGPT when researchers provide fu...
Saved in:
Published in | Journal of medical Internet research Vol. 25; no. 1; p. e51229 |
---|---|
Main Authors | , , , , , , , , , , , , |
Format | Journal Article |
Language | English |
Published |
Canada
Journal of Medical Internet Research
25.12.2023
Gunther Eysenbach MD MPH, Associate Professor JMIR Publications |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | ChatGPT may act as a research assistant to help organize the direction of thinking and summarize research findings. However, few studies have examined the quality, similarity (abstracts being similar to the original one), and accuracy of the abstracts generated by ChatGPT when researchers provide full-text basic research papers.
We aimed to assess the applicability of an artificial intelligence (AI) model in generating abstracts for basic preclinical research.
We selected 30 basic research papers from Nature, Genome Biology, and Biological Psychiatry. Excluding abstracts, we inputted the full text into ChatPDF, an application of a language model based on ChatGPT, and we prompted it to generate abstracts with the same style as used in the original papers. A total of 8 experts were invited to evaluate the quality of these abstracts (based on a Likert scale of 0-10) and identify which abstracts were generated by ChatPDF, using a blind approach. These abstracts were also evaluated for their similarity to the original abstracts and the accuracy of the AI content.
The quality of ChatGPT-generated abstracts was lower than that of the actual abstracts (10-point Likert scale: mean 4.72, SD 2.09 vs mean 8.09, SD 1.03; P<.001). The difference in quality was significant in the unstructured format (mean difference -4.33; 95% CI -4.79 to -3.86; P<.001) but minimal in the 4-subheading structured format (mean difference -2.33; 95% CI -2.79 to -1.86). Among the 30 ChatGPT-generated abstracts, 3 showed wrong conclusions, and 10 were identified as AI content. The mean percentage of similarity between the original and the generated abstracts was not high (2.10%-4.40%). The blinded reviewers achieved a 93% (224/240) accuracy rate in guessing which abstracts were written using ChatGPT.
Using ChatGPT to generate a scientific abstract may not lead to issues of similarity when using real full texts written by humans. However, the quality of the ChatGPT-generated abstracts was suboptimal, and their accuracy was not 100%. |
---|---|
AbstractList | BackgroundChatGPT may act as a research assistant to help organize the direction of thinking and summarize research findings. However, few studies have examined the quality, similarity (abstracts being similar to the original one), and accuracy of the abstracts generated by ChatGPT when researchers provide full-text basic research papers. ObjectiveWe aimed to assess the applicability of an artificial intelligence (AI) model in generating abstracts for basic preclinical research. MethodsWe selected 30 basic research papers from Nature, Genome Biology, and Biological Psychiatry. Excluding abstracts, we inputted the full text into ChatPDF, an application of a language model based on ChatGPT, and we prompted it to generate abstracts with the same style as used in the original papers. A total of 8 experts were invited to evaluate the quality of these abstracts (based on a Likert scale of 0-10) and identify which abstracts were generated by ChatPDF, using a blind approach. These abstracts were also evaluated for their similarity to the original abstracts and the accuracy of the AI content. ResultsThe quality of ChatGPT-generated abstracts was lower than that of the actual abstracts (10-point Likert scale: mean 4.72, SD 2.09 vs mean 8.09, SD 1.03; P<.001). The difference in quality was significant in the unstructured format (mean difference –4.33; 95% CI –4.79 to –3.86; P<.001) but minimal in the 4-subheading structured format (mean difference –2.33; 95% CI –2.79 to –1.86). Among the 30 ChatGPT-generated abstracts, 3 showed wrong conclusions, and 10 were identified as AI content. The mean percentage of similarity between the original and the generated abstracts was not high (2.10%-4.40%). The blinded reviewers achieved a 93% (224/240) accuracy rate in guessing which abstracts were written using ChatGPT. ConclusionsUsing ChatGPT to generate a scientific abstract may not lead to issues of similarity when using real full texts written by humans. However, the quality of the ChatGPT-generated abstracts was suboptimal, and their accuracy was not 100%. Background:ChatGPT may act as a research assistant to help organize the direction of thinking and summarize research findings. However, few studies have examined the quality, similarity (abstracts being similar to the original one), and accuracy of the abstracts generated by ChatGPT when researchers provide full-text basic research papers.Objective:We aimed to assess the applicability of an artificial intelligence (AI) model in generating abstracts for basic preclinical research.Methods:We selected 30 basic research papers from Nature, Genome Biology, and Biological Psychiatry. Excluding abstracts, we inputted the full text into ChatPDF, an application of a language model based on ChatGPT, and we prompted it to generate abstracts with the same style as used in the original papers. A total of 8 experts were invited to evaluate the quality of these abstracts (based on a Likert scale of 0-10) and identify which abstracts were generated by ChatPDF, using a blind approach. These abstracts were also evaluated for their similarity to the original abstracts and the accuracy of the AI content.Results:The quality of ChatGPT-generated abstracts was lower than that of the actual abstracts (10-point Likert scale: mean 4.72, SD 2.09 vs mean 8.09, SD 1.03; P<.001). The difference in quality was significant in the unstructured format (mean difference –4.33; 95% CI –4.79 to –3.86; P<.001) but minimal in the 4-subheading structured format (mean difference –2.33; 95% CI –2.79 to –1.86). Among the 30 ChatGPT-generated abstracts, 3 showed wrong conclusions, and 10 were identified as AI content. The mean percentage of similarity between the original and the generated abstracts was not high (2.10%-4.40%). The blinded reviewers achieved a 93% (224/240) accuracy rate in guessing which abstracts were written using ChatGPT.Conclusions:Using ChatGPT to generate a scientific abstract may not lead to issues of similarity when using real full texts written by humans. However, the quality of the ChatGPT-generated abstracts was suboptimal, and their accuracy was not 100%. ChatGPT may act as a research assistant to help organize the direction of thinking and summarize research findings. However, few studies have examined the quality, similarity (abstracts being similar to the original one), and accuracy of the abstracts generated by ChatGPT when researchers provide full-text basic research papers. We aimed to assess the applicability of an artificial intelligence (AI) model in generating abstracts for basic preclinical research. We selected 30 basic research papers from Nature, Genome Biology, and Biological Psychiatry. Excluding abstracts, we inputted the full text into ChatPDF, an application of a language model based on ChatGPT, and we prompted it to generate abstracts with the same style as used in the original papers. A total of 8 experts were invited to evaluate the quality of these abstracts (based on a Likert scale of 0-10) and identify which abstracts were generated by ChatPDF, using a blind approach. These abstracts were also evaluated for their similarity to the original abstracts and the accuracy of the AI content. The quality of ChatGPT-generated abstracts was lower than that of the actual abstracts (10-point Likert scale: mean 4.72, SD 2.09 vs mean 8.09, SD 1.03; P<.001). The difference in quality was significant in the unstructured format (mean difference –4.33; 95% CI –4.79 to –3.86; P<.001) but minimal in the 4-subheading structured format (mean difference –2.33; 95% CI –2.79 to –1.86). Among the 30 ChatGPT-generated abstracts, 3 showed wrong conclusions, and 10 were identified as AI content. The mean percentage of similarity between the original and the generated abstracts was not high (2.10%-4.40%). The blinded reviewers achieved a 93% (224/240) accuracy rate in guessing which abstracts were written using ChatGPT. Using ChatGPT to generate a scientific abstract may not lead to issues of similarity when using real full texts written by humans. However, the quality of the ChatGPT-generated abstracts was suboptimal, and their accuracy was not 100%. Background ChatGPT may act as a research assistant to help organize the direction of thinking and summarize research findings. However, few studies have examined the quality, similarity (abstracts being similar to the original one), and accuracy of the abstracts generated by ChatGPT when researchers provide full-text basic research papers. Objective We aimed to assess the applicability of an artificial intelligence (AI) model in generating abstracts for basic preclinical research. Methods We selected 30 basic research papers from Nature, Genome Biology, and Biological Psychiatry. Excluding abstracts, we inputted the full text into ChatPDF, an application of a language model based on ChatGPT, and we prompted it to generate abstracts with the same style as used in the original papers. A total of 8 experts were invited to evaluate the quality of these abstracts (based on a Likert scale of 0-10) and identify which abstracts were generated by ChatPDF, using a blind approach. These abstracts were also evaluated for their similarity to the original abstracts and the accuracy of the AI content. Results The quality of ChatGPT-generated abstracts was lower than that of the actual abstracts (10-point Likert scale: mean 4.72, SD 2.09 vs mean 8.09, SD 1.03; P<.001). The difference in quality was significant in the unstructured format (mean difference –4.33; 95% CI –4.79 to –3.86; P<.001) but minimal in the 4-subheading structured format (mean difference –2.33; 95% CI –2.79 to –1.86). Among the 30 ChatGPT-generated abstracts, 3 showed wrong conclusions, and 10 were identified as AI content. The mean percentage of similarity between the original and the generated abstracts was not high (2.10%-4.40%). The blinded reviewers achieved a 93% (224/240) accuracy rate in guessing which abstracts were written using ChatGPT. Conclusions Using ChatGPT to generate a scientific abstract may not lead to issues of similarity when using real full texts written by humans. However, the quality of the ChatGPT-generated abstracts was suboptimal, and their accuracy was not 100%. ChatGPT may act as a research assistant to help organize the direction of thinking and summarize research findings. However, few studies have examined the quality, similarity (abstracts being similar to the original one), and accuracy of the abstracts generated by ChatGPT when researchers provide full-text basic research papers. We aimed to assess the applicability of an artificial intelligence (AI) model in generating abstracts for basic preclinical research. We selected 30 basic research papers from Nature, Genome Biology, and Biological Psychiatry. Excluding abstracts, we inputted the full text into ChatPDF, an application of a language model based on ChatGPT, and we prompted it to generate abstracts with the same style as used in the original papers. A total of 8 experts were invited to evaluate the quality of these abstracts (based on a Likert scale of 0-10) and identify which abstracts were generated by ChatPDF, using a blind approach. These abstracts were also evaluated for their similarity to the original abstracts and the accuracy of the AI content. The quality of ChatGPT-generated abstracts was lower than that of the actual abstracts (10-point Likert scale: mean 4.72, SD 2.09 vs mean 8.09, SD 1.03; P<.001). The difference in quality was significant in the unstructured format (mean difference -4.33; 95% CI -4.79 to -3.86; P<.001) but minimal in the 4-subheading structured format (mean difference -2.33; 95% CI -2.79 to -1.86). Among the 30 ChatGPT-generated abstracts, 3 showed wrong conclusions, and 10 were identified as AI content. The mean percentage of similarity between the original and the generated abstracts was not high (2.10%-4.40%). The blinded reviewers achieved a 93% (224/240) accuracy rate in guessing which abstracts were written using ChatGPT. Using ChatGPT to generate a scientific abstract may not lead to issues of similarity when using real full texts written by humans. However, the quality of the ChatGPT-generated abstracts was suboptimal, and their accuracy was not 100%. |
Audience | Academic |
Author | Tseng, Ping-Tao Hsu, Tien-Wei Cheng, Shu-Li Tsai, Shih-Jen Bai, Ya-Mei Tsai, Chia-Kuang Yang, Fu-Chi Su, Kuan-Pin Liang, Chih-Sung Tu, Yu-Kang Yang, Szu-Nian Ko, Chih-Hung Hsu, Chih-Wei |
AuthorAffiliation | 19 Department of Psychiatry Tri-service Hospital Beitou branch Taipei Taiwan 3 Division of Psychiatry, School of Medicine, National Yang-Ming University Taipei Taiwan 2 Department of Psychiatry Taipei Veterans General Hospital Taipei Taiwan 4 Department of Psychiatry Kaohsiung Medical University Hospital Kaohsiung Taiwan 1 Department of Nursing Mackay Medical College Taipei Taiwan 15 Department of Psychology College of Medical and Health Science Asia University Taichung Taiwan 17 Department of Psychiatry E-Da Dachang Hospital I-Shou University Kaohsiung Taiwan 13 Graduate Institute of Health and Welfare Policy National Yang Ming Chiao Tung University Taipei Taiwan 6 Department of Psychiatry Kaohsiung Municipal Siaogang Hospital Kaohsiung Medical University Kaohsiung Taiwan 16 Prospect Clinic for Otorhinolaryngology and Neurology Kaohsiung Taiwan 9 Institute of Epidemiology and Preventive Medicine College of Public Health National Taiwan University Taipei Taiwan 12 Department of Psychiatry Armed F |
AuthorAffiliation_xml | – name: 13 Graduate Institute of Health and Welfare Policy National Yang Ming Chiao Tung University Taipei Taiwan – name: 21 College of Medicine China Medical University Taichung Taiwan – name: 22 Mind-Body Interface Laboratory China Medical University and Hospital Taichung Taiwan – name: 5 Department of Psychiatry College of Medicine Kaohsiung Medical University Kaohsiung Taiwan – name: 17 Department of Psychiatry E-Da Dachang Hospital I-Shou University Kaohsiung Taiwan – name: 14 Institute of Biomedical Sciences Institute of Precision Medicine National Sun Yat-sen University Kaohsiung Taiwan – name: 3 Division of Psychiatry, School of Medicine, National Yang-Ming University Taipei Taiwan – name: 4 Department of Psychiatry Kaohsiung Medical University Hospital Kaohsiung Taiwan – name: 11 Department of Psychiatry Tri-service Hospital, Beitou branch Taipei Taiwan – name: 18 Department of Psychiatry E-Da Hospital I-Shou University Kaohsiung Taiwan – name: 10 Department of Dentistry National Taiwan University Hospital Taipei Taiwan – name: 12 Department of Psychiatry Armed Forces Taoyuan General Hospital Taoyuan Taiwan – name: 2 Department of Psychiatry Taipei Veterans General Hospital Taipei Taiwan – name: 8 Department of Neurology Tri-Service General Hospital National Defense Medical Center Taipei Taiwan – name: 23 An-Nan Hospital China Medical University Tainan Taiwan – name: 6 Department of Psychiatry Kaohsiung Municipal Siaogang Hospital Kaohsiung Medical University Kaohsiung Taiwan – name: 7 Department of Psychiatry Kaohsiung Chang Gung Memorial Hospital Kaohsiung Taiwan – name: 15 Department of Psychology College of Medical and Health Science Asia University Taichung Taiwan – name: 16 Prospect Clinic for Otorhinolaryngology and Neurology Kaohsiung Taiwan – name: 1 Department of Nursing Mackay Medical College Taipei Taiwan – name: 9 Institute of Epidemiology and Preventive Medicine College of Public Health National Taiwan University Taipei Taiwan – name: 19 Department of Psychiatry Tri-service Hospital Beitou branch Taipei Taiwan – name: 20 Department of Psychiatry National Defense Medical Center Taipei Taiwan |
Author_xml | – sequence: 1 givenname: Shu-Li orcidid: 0000-0002-1523-8519 surname: Cheng fullname: Cheng, Shu-Li organization: Department of Nursing, Mackay Medical College, Taipei, Taiwan – sequence: 2 givenname: Shih-Jen orcidid: 0000-0002-9987-022X surname: Tsai fullname: Tsai, Shih-Jen organization: Division of Psychiatry, School of Medicine, National Yang-Ming University, Taipei, Taiwan – sequence: 3 givenname: Ya-Mei orcidid: 0000-0003-3779-9074 surname: Bai fullname: Bai, Ya-Mei organization: Division of Psychiatry, School of Medicine, National Yang-Ming University, Taipei, Taiwan – sequence: 4 givenname: Chih-Hung orcidid: 0000-0001-8034-0221 surname: Ko fullname: Ko, Chih-Hung organization: Department of Psychiatry, Kaohsiung Municipal Siaogang Hospital, Kaohsiung Medical University, Kaohsiung, Taiwan – sequence: 5 givenname: Chih-Wei orcidid: 0000-0002-8650-4060 surname: Hsu fullname: Hsu, Chih-Wei organization: Department of Psychiatry, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan – sequence: 6 givenname: Fu-Chi orcidid: 0000-0001-6831-3634 surname: Yang fullname: Yang, Fu-Chi organization: Department of Neurology, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan – sequence: 7 givenname: Chia-Kuang orcidid: 0000-0001-7693-1408 surname: Tsai fullname: Tsai, Chia-Kuang organization: Department of Neurology, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan – sequence: 8 givenname: Yu-Kang orcidid: 0000-0002-2461-474X surname: Tu fullname: Tu, Yu-Kang organization: Department of Dentistry, National Taiwan University Hospital, Taipei, Taiwan – sequence: 9 givenname: Szu-Nian orcidid: 0000-0002-6091-0263 surname: Yang fullname: Yang, Szu-Nian organization: Graduate Institute of Health and Welfare Policy, National Yang Ming Chiao Tung University, Taipei, Taiwan – sequence: 10 givenname: Ping-Tao orcidid: 0000-0001-5761-7800 surname: Tseng fullname: Tseng, Ping-Tao organization: Prospect Clinic for Otorhinolaryngology and Neurology, Kaohsiung, Taiwan – sequence: 11 givenname: Tien-Wei orcidid: 0000-0003-4136-1251 surname: Hsu fullname: Hsu, Tien-Wei organization: Department of Psychiatry, E-Da Hospital, I-Shou University, Kaohsiung, Taiwan – sequence: 12 givenname: Chih-Sung orcidid: 0000-0003-1138-5586 surname: Liang fullname: Liang, Chih-Sung organization: Department of Psychiatry, National Defense Medical Center, Taipei, Taiwan – sequence: 13 givenname: Kuan-Pin orcidid: 0000-0002-4501-2502 surname: Su fullname: Su, Kuan-Pin organization: An-Nan Hospital, China Medical University, Tainan, Taiwan |
BackLink | https://www.ncbi.nlm.nih.gov/pubmed/38145486$$D View this record in MEDLINE/PubMed |
BookMark | eNptkttu1DAQhiNURA_0FVAkhARSU2zHcZzeoHYFbaWK0xZxaU182LpK7MV2gH0OXhhvW0oXIV_YGn_z2zPz7xZbzjtdFPsYHRLcsdcNJqR7VOxgWvOK8xZvPThvF7sxXiNEEO3wk2K75pg2lLOd4tfMj0sINnoXS2_KTxMMNq0OypkPQcvkdIwHJThVzu1oh0ymVXmi0w-tXTm7gnT68bI61U4HSFrdgGfTCK76msmUmeM-pgAyxdL4UJ5AtLL8rKOGIK-OylnwMVbz_JD1DoZynia1elo8NjBEvX-37xVf3r29nJ1VFx9Oz2fHF5Vsmi5VCjVcS1A97jRpJAFGGEcgwVCFuaI97VmNes2QMYgZQxpOCW6h1YzUCqF6rzi_1VUersUy2BHCSniw4ibgw0JASFYOWqAGcINq2puW05rJXnHgtDHAekVor7LWm1ut5dSPWkntctXDhujmjbNXYuG_C4xahijmWeHlnULw3yYdkxhtlHoYwGk_RUE61LQcM7z--PN_0Gs_hdy_NYVbRrpc6l9qAbkC64xfD2ItKo7blteENV2bqcP_UHkpPVqZPWZsjm8kvNpIyEzSP9MCphjF-fz9JvvilpXrOQdt7huCkVjbVtzYNnPPHnbvnvrj0_o3kCDn3w |
CitedBy_id | crossref_primary_10_3390_bioengineering11040342 crossref_primary_10_2196_56500 crossref_primary_10_2196_57978 |
Cites_doi | 10.1186/s13054-023-04380-2 10.2139/ssrn.4429014 10.1136/bmj.p1133 10.1016/S2589-7500(23)00023-7 10.2196/46924 10.3390/healthcare11060887 10.1038/s41746-023-00819-6 |
ContentType | Journal Article |
Copyright | Shu-Li Cheng, Shih-Jen Tsai, Ya-Mei Bai, Chih-Hung Ko, Chih-Wei Hsu, Fu-Chi Yang, Chia-Kuang Tsai, Yu-Kang Tu, Szu-Nian Yang, Ping-Tao Tseng, Tien-Wei Hsu, Chih-Sung Liang, Kuan-Pin Su. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 25.12.2023. COPYRIGHT 2023 Journal of Medical Internet Research 2023. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. Shu-Li Cheng, Shih-Jen Tsai, Ya-Mei Bai, Chih-Hung Ko, Chih-Wei Hsu, Fu-Chi Yang, Chia-Kuang Tsai, Yu-Kang Tu, Szu-Nian Yang, Ping-Tao Tseng, Tien-Wei Hsu, Chih-Sung Liang, Kuan-Pin Su. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 25.12.2023. 2023 |
Copyright_xml | – notice: Shu-Li Cheng, Shih-Jen Tsai, Ya-Mei Bai, Chih-Hung Ko, Chih-Wei Hsu, Fu-Chi Yang, Chia-Kuang Tsai, Yu-Kang Tu, Szu-Nian Yang, Ping-Tao Tseng, Tien-Wei Hsu, Chih-Sung Liang, Kuan-Pin Su. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 25.12.2023. – notice: COPYRIGHT 2023 Journal of Medical Internet Research – notice: 2023. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: Shu-Li Cheng, Shih-Jen Tsai, Ya-Mei Bai, Chih-Hung Ko, Chih-Wei Hsu, Fu-Chi Yang, Chia-Kuang Tsai, Yu-Kang Tu, Szu-Nian Yang, Ping-Tao Tseng, Tien-Wei Hsu, Chih-Sung Liang, Kuan-Pin Su. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 25.12.2023. 2023 |
DBID | CGR CUY CVF ECM EIF NPM AAYXX CITATION ISN 3V. 7QJ 7RV 7X7 7XB 8FI 8FJ 8FK ABUWG AFKRA ALSLI AZQEC BENPR CCPQU CNYFK DWQXO E3H F2A FYUFA GHDGH K9. KB0 M0S M1O NAPCQ PIMPY PQEST PQQKQ PQUKI 7X8 5PM DOA |
DOI | 10.2196/51229 |
DatabaseName | Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed CrossRef Gale In Context: Canada ProQuest Central (Corporate) Applied Social Sciences Index & Abstracts (ASSIA) ProQuest Nursing and Allied Health Journals ProQuest - Health & Medical Complete保健、医学与药学数据库 ProQuest Central (purchase pre-March 2016) Hospital Premium Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland Social Science Premium Collection (Proquest) (PQ_SDU_P3) ProQuest Central Essentials AUTh Library subscriptions: ProQuest Central ProQuest One Community College Library & Information Science Collection ProQuest Central Library & Information Sciences Abstracts (LISA) Library & Information Science Abstracts (LISA) Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Health & Medical Complete (Alumni) Nursing & Allied Health Database (Alumni Edition) Health & Medical Collection (Alumni Edition) Library Science Database Nursing & Allied Health Premium Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition MEDLINE - Academic PubMed Central (Full Participant titles) Directory of Open Access Journals |
DatabaseTitle | MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) CrossRef Publicly Available Content Database Library and Information Science Abstracts (LISA) ProQuest Central Essentials ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) ProQuest One Community College Applied Social Sciences Index and Abstracts (ASSIA) ProQuest Central ProQuest Library Science Health Research Premium Collection Health and Medicine Complete (Alumni Edition) ProQuest Central Korea Library & Information Science Collection Social Science Premium Collection ProQuest One Academic Eastern Edition ProQuest Nursing & Allied Health Source ProQuest Hospital Collection Health Research Premium Collection (Alumni) ProQuest Hospital Collection (Alumni) Nursing & Allied Health Premium ProQuest Health & Medical Complete ProQuest One Academic UKI Edition ProQuest Nursing & Allied Health Source (Alumni) ProQuest One Academic ProQuest Central (Alumni) MEDLINE - Academic |
DatabaseTitleList | Publicly Available Content Database CrossRef MEDLINE - Academic MEDLINE |
Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database – sequence: 4 dbid: BENPR name: AUTh Library subscriptions: ProQuest Central url: https://www.proquest.com/central sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Medicine Library & Information Science Biology |
EISSN | 1438-8871 |
EndPage | e51229 |
ExternalDocumentID | oai_doaj_org_article_05a15034bf78436cbd8a845fa6bd24bd A778326597 10_2196_51229 38145486 |
Genre | Journal Article |
GroupedDBID | --- .4I .DC 29L 2WC 36B 53G 5GY 5VS 77K 7RV 7X7 8FI 8FJ AAFWJ AAKPC AAWTL ABDBF ABIVO ABUWG ACGFO ADBBV AEGXH AENEX AFKRA AFPKN AIAGR ALIPV ALMA_UNASSIGNED_HOLDINGS ALSLI AOIJS BAWUL BCNDV BENPR CCPQU CGR CNYFK CS3 CUY CVF DIK DU5 DWQXO E3Z EAP EBD EBS ECM EIF EJD ELW EMB EMOBN ESX F5P FRP FYUFA GROUPED_DOAJ GX1 HMCUK HYE IAO ICO IEA IHR INH ISN ITC KQ8 M1O M48 NAPCQ NPM OK1 P2P PGMZT PIMPY PQQKQ RNS RPM SJN SV3 TR2 UKHRP XSB AAYXX CITATION 3V. 7QJ 7XB 8FK AZQEC E3H F2A K9. PQEST PQUKI 7X8 5PM |
ID | FETCH-LOGICAL-c559t-d058ecadb19e25c2a62680acaf4d18d4b4b630be60ff06ff2584217a7e623d003 |
IEDL.DBID | RPM |
ISSN | 1438-8871 1439-4456 |
IngestDate | Tue Oct 22 15:12:33 EDT 2024 Tue Sep 17 21:29:07 EDT 2024 Fri Aug 16 20:43:31 EDT 2024 Thu Oct 10 22:44:11 EDT 2024 Fri Feb 23 00:21:29 EST 2024 Tue Jan 09 05:07:15 EST 2024 Thu Aug 01 20:04:35 EDT 2024 Thu Sep 26 17:07:04 EDT 2024 Wed Oct 23 10:03:54 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 1 |
Keywords | generation scientific research natural language processing abstracts plagiarism language model AI-generated scientific content abstract LLM academic research extraction artificial intelligence textual generative NLP extract ChatGPT publication text language models publications |
Language | English |
License | Shu-Li Cheng, Shih-Jen Tsai, Ya-Mei Bai, Chih-Hung Ko, Chih-Wei Hsu, Fu-Chi Yang, Chia-Kuang Tsai, Yu-Kang Tu, Szu-Nian Yang, Ping-Tao Tseng, Tien-Wei Hsu, Chih-Sung Liang, Kuan-Pin Su. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 25.12.2023. This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in the Journal of Medical Internet Research, is properly cited. The complete bibliographic information, a link to the original publication on https://www.jmir.org/, as well as this copyright and license information must be included. |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c559t-d058ecadb19e25c2a62680acaf4d18d4b4b630be60ff06ff2584217a7e623d003 |
Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
ORCID | 0000-0001-5761-7800 0000-0002-9987-022X 0000-0001-6831-3634 0000-0002-6091-0263 0000-0001-7693-1408 0000-0002-1523-8519 0000-0002-8650-4060 0000-0002-4501-2502 0000-0002-2461-474X 0000-0003-4136-1251 0000-0003-1138-5586 0000-0001-8034-0221 0000-0003-3779-9074 |
OpenAccessLink | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10760418/ |
PMID | 38145486 |
PQID | 2917629584 |
PQPubID | 2033121 |
ParticipantIDs | doaj_primary_oai_doaj_org_article_05a15034bf78436cbd8a845fa6bd24bd pubmedcentral_primary_oai_pubmedcentral_nih_gov_10760418 proquest_miscellaneous_2905781610 proquest_journals_2917629584 gale_infotracmisc_A778326597 gale_infotracacademiconefile_A778326597 gale_incontextgauss_ISN_A778326597 crossref_primary_10_2196_51229 pubmed_primary_38145486 |
PublicationCentury | 2000 |
PublicationDate | 2023-12-25 |
PublicationDateYYYYMMDD | 2023-12-25 |
PublicationDate_xml | – month: 12 year: 2023 text: 2023-12-25 day: 25 |
PublicationDecade | 2020 |
PublicationPlace | Canada |
PublicationPlace_xml | – name: Canada – name: Toronto – name: Toronto, Canada |
PublicationTitle | Journal of medical Internet research |
PublicationTitleAlternate | J Med Internet Res |
PublicationYear | 2023 |
Publisher | Journal of Medical Internet Research Gunther Eysenbach MD MPH, Associate Professor JMIR Publications |
Publisher_xml | – name: Journal of Medical Internet Research – name: Gunther Eysenbach MD MPH, Associate Professor – name: JMIR Publications |
References | ref8 ref7 ref9 ref4 ref3 ref6 ref11 ref5 ref10 ref2 ref1 |
References_xml | – ident: ref1 doi: 10.1186/s13054-023-04380-2 – ident: ref4 doi: 10.2139/ssrn.4429014 – ident: ref5 – ident: ref7 – ident: ref2 doi: 10.1136/bmj.p1133 – ident: ref9 – ident: ref8 – ident: ref10 doi: 10.1016/S2589-7500(23)00023-7 – ident: ref11 doi: 10.2196/46924 – ident: ref6 doi: 10.3390/healthcare11060887 – ident: ref3 doi: 10.1038/s41746-023-00819-6 |
SSID | ssj0020491 |
Score | 2.4755437 |
Snippet | ChatGPT may act as a research assistant to help organize the direction of thinking and summarize research findings. However, few studies have examined the... Background ChatGPT may act as a research assistant to help organize the direction of thinking and summarize research findings. However, few studies have... Background ChatGPT may act as a research assistant to help organize the direction of thinking and summarize research findings. However, few studies have... Background:ChatGPT may act as a research assistant to help organize the direction of thinking and summarize research findings. However, few studies have... BACKGROUNDChatGPT may act as a research assistant to help organize the direction of thinking and summarize research findings. However, few studies have... BackgroundChatGPT may act as a research assistant to help organize the direction of thinking and summarize research findings. However, few studies have... |
SourceID | doaj pubmedcentral proquest gale crossref pubmed |
SourceType | Open Website Open Access Repository Aggregation Database Index Database |
StartPage | e51229 |
SubjectTerms | Accuracy Artificial Intelligence Biology Chatbots Computational linguistics Cross-Sectional Studies Genomes Genomics Humans Language Language processing Likert scale Multimedia Natural language interfaces Original Paper Plagiarism Psychiatry Research Personnel Variables |
SummonAdditionalLinks | – databaseName: Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELZQDxUSQlBegbYyCMGlUR2vk3i57UaUgtQKaVupN8tPugeyiGQP_R38YWYc77IRBy5cM44Uz4xnvs8Zjwl567CLGJPT3Pqa55Bvea6ZDjkzU25Y6SFF4T7kxWV1fi2-3JQ3O1d9YU3Y0B54UNwpKzVglokwoZZiUlnjpJaiDLoyjgvjYvQtyg2ZSlQLcG-xTx5goTO42ClktYgh_2Se2KD_7zC8k4fGNZI7SefsEXmY0CKdDV_5mNzz7QE5SmcN6DuaDhOhcmlapQdk_yL9L39CfjXbawY7ugp06Jhxd0IbvJTD9hjnTqhuHV0svy-B5IKQzofSLdrc6v7T16t86EwNyDQOjLv-OZD6HtA2nRncKrF9R-FD6FyDzemmmO8DbVAR-SJWe-E8sGjx7im5Pvt41Zzn6RqG3ALd6HPHSumtdqaYel5aroEDSaatDsIV0gkjTDVhxlcsBFaFwAHTANHRtQdo5SBqPCN77ar1LwiVSLeCFM6GWtga_EQbw6WZGO0DQMWMHG9MpH4M3TYUsBS0oYo2zMgcDbcVYnPs-ABcRiWXUf9ymYy8QbMrbH_RYn3NN73uOvV5calmdQ0hrgKWlZH3aVBYoSJ1Oq4AE8GOWaORh6ORsD7tWLzxLpXiQ6c4sOSKT0FTGXm9FeObWPPW-tUaxwCWloDIWUaeD864nTfgLAFcs8qIHLnpSDFjSbu8jd3DC_wXKwr58n-o8hW5zwH1YX0PLw_JXv9z7Y8ApfXmOC7I35lUPQU priority: 102 providerName: Directory of Open Access Journals – databaseName: Library Science Database dbid: M1O link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3db9MwED_BEBMS4qN8BbbJIAQvy5a4TuLygtqKMZA2kLppe4v8EW8VIhlr-lD-Df5h7hK3W0DigdfeVbKd893v7J_vAF5bqiIWyUFoioyHGG95qCLlwkgPuI6SAkMUnUMeHKb7x-LzaXLqD9xmnla59ImNo7aVoTPyXY55RcoHGC_fX_wIqWsU3a76Fho34VZMpfGIuhd_WSVciH7jdbhLdGeU7mJsa5DkVfxpyvT_7YyvRaMuU_Ja6Nm7D_ly0C3j5NvOvNY75ucf9Rz_f1YP4J5HpWzYmtFDuFGUPbjd9qlc9GDTv25gb5h_vkSfk3m_0IP1A39D_wh-jVeNDWescqyt0bHYZmNqA2Jq8qzbTJWWTabfp5hWo5CNWrIYG5-r-uPXo7CthY1YuFFs7hnCE9REfM-Gmg5nTD1jOBA2UmhlbEkffMfGtOjhpOGX0YyIJrl4DMd7H47G-6Fv_BAaTHDq0EaJLIyyOh4UPDFcYdYlI2WUEzaWVmih036kizRyLkqd47h-mFqprEAwZ9FPPYG1siqLZ8AkJXhOCmtcJkyGlqm05lL3tSocgtMAtpbmkF-09T1yzIvIXvLGXgIYkZGshFSOu_mhujzL_e7Oo0QhsO4L7TIp-qnRViopEqdSbbnQNoBXZGI5FdwoidFzpuazWf5pcpgPswydaop5XQBvvZKraCGVfyCBE6EaXR3NjY4megTTFS-NLfceaZZfWVoAL1di-iex7MqimpMOoneJOUAUwNPW8FfzRmQnMLtNA5CdLdFZmK6knJ439cpjuv0VsXz-73G9gDscESRxhXiyAWv15bzYRMRX661mW_8GOVhaJw priority: 102 providerName: ProQuest – databaseName: Scholars Portal Journals: Open Access(OpenAccess) dbid: M48 link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1ti9NAEB70hEMQ0fMtenesIvrlcm43m2QriLTF8xR6CL2C38K-3hU01TYF-zv8w84kaWnQj37tTqA7LzvP7D47C_DSURcxrvqx9bmIMd-KWHMdYm76wvDUY4qifcjxRXY-lZ-_pjtswlaBy3-WdvSe1HTx7fTXz_V7DPh3RGNGB3qDOUv0b8ItIRNJTj6W24MEgQC4tw93OqKdFFR36v97Pd5JSF2y5E72ObsHd1vYyAaNne_DDV8ewFF76YC9Yu2tItIya8P1APbH7cH5A_g92r43uGTzwJrWGesTNqLXOWxFC94J06Vjk9n3GaoEB9mw4XCx0bWuPn65jJsW1QhRa8F6-z_G6r5C2M0GhvZMbLVk-EfYUKPx2YbV95aNSBHxpKZ90TyIvbh-CNOzD5ej87h9jyG2WHdUseOp8lY70-t7kVqhsRhSXFsdpOspJ400WcKNz3gIPAtBILjBikfnHjGWw-XjEeyV89I_Aaao7gpKOhtyaXN0GG2MUCYx2gfEjBEcb0xU_GjabhRYrpANi9qGEQzJcNtB6pJd_zBfXBVt0BU81Yh3E2lCrmSSWeOUVjINOjNOSOMieEFmL6gPRklEmyu9Wi6LT5OLYpDnuNZlWG5F8LoVCnNSpG7vLeBEqHVWR_KwI4mBarvDG-8qNn5eCCyXM9FHTUXwfDtMXxL5rfTzFckgqFYIzXkEjxtn3M4bAZfEojOLQHXctKOY7kg5u67biPfoUFb21NP_ocpncFsg_COij0gPYa9arPwRwrXKHNcB-QeBv0G2 priority: 102 providerName: Scholars Portal |
Title | Comparisons of Quality, Correctness, and Similarity Between ChatGPT-Generated and Human-Written Abstracts for Basic Research: Cross-Sectional Study |
URI | https://www.ncbi.nlm.nih.gov/pubmed/38145486 https://www.proquest.com/docview/2917629584 https://search.proquest.com/docview/2905781610 https://pubmed.ncbi.nlm.nih.gov/PMC10760418 https://doaj.org/article/05a15034bf78436cbd8a845fa6bd24bd |
Volume | 25 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Bb9MwFH7ahjQhIQQDRmCrDEJwWdbUcRKXWxttDKSWim7SbpHtxFslmk5retjv4A_znpNUi7hxySF2pNh-z-_77M_PAJ9yyiIWyKFvioT7GG-5rwJl_UAPuQ6iAkMUrUNOpvHFlfhxHV3vQNyehXGifaMXp-Xv5Wm5uHXayrul6bc6sf5skg5oO0kMZH8XdpMwbDl6Q7MQ8zqaJWiPE_HBPjwjwTOaWh-jG6c8oRimBEL1uBOMXM7-f2fmR6GpK5t8FIfOX8DzBkCyUf2jL2GnKA_guDl-wD6z5nwR9TdrHPcA9ifNFvor-JNubx5cs5VldRKNhxOW0j0dpqKp74SpMmfzxXKBvBcL2bhWc7H0VlXfZpd-nawawaqr6DYCfOT5FQJwNtK0emKqNcMfYWOFZsBafd9XllJH-HMnAKN2kI7x4TVcnZ9dphd-czODb5CBVH4eRLIwKteDYcEjwxXSIhkoo6zIBzIXWug4DHQRB9YGsbUcYQ5yH5UUiLZynEjewF65Kou3wCQxMCtFbmwiTIKmo7TmUodaFRbRowe9doiyuzoBR4bEhYYzc8PpwZgGbltI-bLdi9X9TdZYTRZECpFvKLRNpAhjo3OppIisinXOhc49-EjDnlFGjJIkNzdqs15n3-fTbJQkOOvFSLw8-NJUsivqSNWcYMCGUBKtTs2jTk10WdMtbq0ra6aMdcaROMd8iD3lwYdtMX1JMriyWG2oDsJriSA98OCwNsZtu1ub9kB2zLTTMd0S9C-XULz1p3f__-l7eMoR_pHQh0dHsFfdb4pjhGuV7qGPXic9eDI-m85-9dyiBz4ng5_0FLLnvPcvQSVEkw |
link.rule.ids | 230,315,733,786,790,870,891,2115,11965,12083,21416,24346,27955,27956,31752,31753,33777,33778,36208,36209,43343,43838,44419,74100,74657,75273 |
linkProvider | National Library of Medicine |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1Lb9NAEB5BKgoSQhBehrYsCMGlVp2NHxsuKIlaUmiiiqZSb9Y-vG0O2KV2Dvkd_GFm7E1aC4lrZiN5d2Znvm93dgbgo6EqYoEY-DpLuI_xlvsykNYP1ICrIMowRNE55HQWT87D7xfRhTtwK11a5don1o7aFJrOyA848oqYDzBefr3-7VPXKLpddS007sMWldwUHdgaHc5Of24oF-Lf3jY8poRnNLUDjG41lryNQHWh_n_d8Z141M6VvBN8jp7CE4ca2bBR8zO4l-VdeND0kVx1Yde9PmCfmHteRMvN3L7twvbU3aA_hz_jTePBkhWWNTU0VvtsTG06dEWeb5_J3LCzxa8F0l4UslGTzMXGV7L6djr3m1rViFXrgfU9gI80v0L8zYaKDk90VTL8EDaSaAVsnd73hY1pSfyzOv-LZkRpjKsXcH50OB9PfNeYwddIQCrfBJHItDSqN8h4pLlEViQCqaUNTU-YUIUq7gcqiwNrg9hajlpD6iOTDMGWQT_yEjp5kWevgQkiYFaERtsk1AlajlSKC9VXMrMIHj3YWysrvW7qb6TIW0ibaa1ND0akwo2QymXXPxQ3l6nbfWkQSQS-_VDZRIT9WCsjpAgjK2NleKiMBx_IAFIqiJFTxs2lXJZlenw2S4dJgk4vRt7lwWc3yBa0kNI9YMCJUA2t1sid1kjcsbotXttZ6jxGmd7atwfvN2L6J2XB5VmxpDGIrgVi9MCDV41ZbuaNyCtE9hl7IFoG21qYtiRfXNX1xHt0Oxv2xJv_f9c7eDiZT0_Sk-PZj7fwiCPao7weHu1Ap7pZZruIziq157bgXy_sO3w |
linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3db9MwELdgiAoJIShfgW0YhOBlUV3XSVxeUFsoG7BqUjepb5E_4q0PJGNJH_p38A9zl7jtIiRee64U-853v599viPkvcUqYkwOQ5MlPIR4y0PFlAuZHnLNogxCFJ5Dns7i4wvxfREtfP5T6dMqNz6xdtS2MHhG3uPAK2I-hHjZcz4t4uzL9PP17xA7SOFNq2-ncZfcgyjJsI1DstiRL0DC_Q55iKnPYHQ9iHM1qtzForpk_7-O-VZkamdN3gpD08fkkcePdNQo_Am5k-Vdcr_pKLnukgP_DoF-oP6hES489Tu4Szqn_i79Kfkz2bYgLGnhaFNNY31EJ9iww1ToA4-oyi2dL38tgQCDkI6btC46uVLVt7PzsKlaDai1HljfCIRA-CtA4nSk8RjFVCWFD6FjBfZAN4l-n-gElySc15lgOCNMaFw_IxfTr-eT49C3aAgNUJEqtCySmVFW94cZjwxXwI8kU0Y5YfvSCi10PGA6i5lzLHaOg_6ABKkkA9hlwaM8J3t5kWcvCZVIxZwU1rhEmARsSGnNpR5olTmAkQE53CgrvW4qcaTAYFCbaa3NgIxRhVshFs6ufyhuLlO_D1MWKYDAA6FdIsUgNtpKJUXkVKwtF9oG5B0aQIqlMXI0sku1Ksv0ZD5LR0kC7i8GBhaQj36QK3AhlX_KABPBalqtkfutkbB3TVu8sbPU-44y3Vl6QN5uxfhPzIfLs2KFYwBnS0DrLCAvGrPczhswmAAeGgdEtgy2tTBtSb68qiuL9_GeVvTlq_9_1xvSgb2X_jyZ_XhNHnCAfZjgw6N9slfdrLIDgGmVPqz3319xrD45 |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Comparisons+of+Quality%2C+Correctness%2C+and+Similarity+Between+ChatGPT-Generated+and+Human-Written+Abstracts+for+Basic+Research%3A+Cross-Sectional+Study&rft.jtitle=Journal+of+medical+Internet+research&rft.au=Shu-Li+Cheng&rft.au=Shih-Jen+Tsai&rft.au=Ya-Mei+Bai&rft.au=Chih-Hung+Ko&rft.date=2023-12-25&rft.pub=JMIR+Publications&rft.eissn=1438-8871&rft.volume=25&rft.spage=e51229&rft_id=info:doi/10.2196%2F51229&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_05a15034bf78436cbd8a845fa6bd24bd |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1438-8871&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1438-8871&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1438-8871&client=summon |