Skip to main content
Springer Nature Link
Log in

Is ChatGPT Able to Generate Texts that Are Easy to Understand and Read?

  • Conference paper
  • First Online:
Good Practices and New Perspectives in Information Systems and Technologies (WorldCIST 2024)

Part of the book series: Lecture Notes in Networks and Systems ((LNNS,volume 987))

Included in the following conference series:

  • 454 Accesses

Abstract

The emergence of generative artificial intelligence applications in recent years has opened up the possibility of automatically generating text tailored to the needs of users. However, is the text generated by these tools easily readable and understandable? This study aims to analyze the ChatGPT's capacity to generate easy to understand texts in Spanish, while adhering to the recommended guidelines for Plain Language. The comprehensiveness of several websites belonging to the Public Administration in Spain has been analyzed. Moreover, ChatGPT was requested to enhance these texts in accordance with the guidelines of Plain Language in Spanish. The original texts and those generated by ChatGPT were then compared to analyze the primary linguistic indicators of different Plain Language guidelines. The study presents a quantitative analysis demonstrating that the new texts generated by ChatGPT do not adhere to Plain Language guidelines. Additionally, the study highlights the use of linguistic elements that should be avoided.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Morato, J., Iglesias, A., Campillo, A., Sanchez-Cuadrado, S.:  Automated readability assessment for Spanish e-Government information. J. Inform. Syst. Eng. Manag. 5(1) (2021).  e-ISSN: 2468–4376

    Google Scholar 

  2. Public Law 111–274-oct. 13, 2010. 124. Stat. 2861. 111th Congress. Plain Writing Act of (2010).  https://www.govinfo.gov/content/pkg/PLAW-111publ274/pdf/PLAW-111publ274.pdf

  3. Campillo, A, Sánchez-Cuadrado, S, Iglesias, A, Morato, J.: Influence of term familiarity in readability of spanish e-Government web information. In: Future Technologies Conference, FTC 2020, 5–6 November (2020)

    Google Scholar 

  4. European Commission. 2019 Clear writing for Europe Conference (2019a). https://ec.europa.eu/info/sites/info/files/clear_writing_conference_notes_for_website.pdf. (Accessed 30 Apr 2020)

  5. European Commission Commission Style Guide (2019). https://ec.europa.eu/information_society/newsroom/. (Accessed 30 Apr 2020)

  6. Fruhlinger, J.:. ¿Qué es y cómo funciona la IA generativa? Computerworld Spain, NA (2023). https://link.gale.com/apps/doc/A758619517/IFME?u=anon~7f439a8d&sid=googleScholar&xid=660a6e76

  7. Olite, F.M.D., Suárez, I.D.R.M., Ledo, M.J.V.:  Chat GPT: origen, evolución, retos e impactos en la educación. Educación Médica Superior 37(2) (2023)

    Google Scholar 

  8. Teixeira da Silva, J.A.:  Can ChatGPT rescue or assist with language barriers in healthcare communication?. Patient Educ. Counseling 115, 107940 (2023). https://doi.org/10.1016/j.pec.2023.107940

  9. Ali, S.R., Dobbs, T.D., Hutchings, H.A., Whitaker, I.S.: Using ChatGPT to write patient clinic letters. Lancet Digital Health 5(4), e179-e81 (2023) . https://www.thelancet.com/journals/landig/article/PIIS2589-7500(23)00048-1

  10. Moons, P., Van Bulck, L.: Using ChatGPT and Google Bard to improve the readability of written patient information: a proof of concept. Euro. J. Cardiovascular Nursing zvad087 (2023). https://doi.org/10.1093/eurjcn/zvad087

  11. Ayre, J., Mac, O., McCaffery, K., et al.: New Frontiers in health literacy: using ChatGPT to simplify health information for people in the community. J. Gen. Intern. Med. (2023). https://doi.org/10.1007/s11606-023-08469-w

  12. Lyu, Q., Tan, J., Zapadka, M.E., Ponnatapura, J., Niu, C., Myers, K.J., et al.: Translating radiology reports into plain language using ChatGPT and GPT-4 with prompt learning: results, limitations, and potential. Visual Comput. Indust. Biomed. Art 6(1), 9 (2023)

    Article  Google Scholar 

  13. Akiba, D., Fraboni, M.C.: AI-supported academic advising: exploring chatgpt’s current state and future potential toward student empowerment. Educ. Sci. 13(9), 885 (2023). https://doi.org/10.3390/educsci13090885

    Article  Google Scholar 

  14. Ayinde, L., Wibowo, M.P., Ravuri, B., Emdad, F.B.: ChatGPT as an important tool in organizational management: a review of the literature. Bus. Inf. Rev. 40(3), 137–149 (2023). https://doi.org/10.1177/02663821231187991

    Article  Google Scholar 

  15. Tan, J., Westermann, H., and Benyekhlef, K.:  ChatGPT as an Artificial Lawyer?. Artificial Intelligence for Access to Justice (AI4AJ 2023) (2023). https://ceur-ws.org/Vol-3435/short2.pdf

  16. Westermann, H, and Benyekhlef, K. (2023). Justicebot: A methodology for building augmented intelligence tools for laypeople to increase access to justice. Proceedings of the Nineteenth International Conference on Artificial Intelligence and Law

    Google Scholar 

  17. Iglesias, A., Cobián, I., Campillo, A., Morato, J., Sánchez-Cuadrado, S.: Comp4Text Checker: an automatic and visual evaluation tool to check the readability of spanish web pages. In: Miesenberger, K., Manduchi, R., Covarrubias Rodriguez, M., Peňá, P. (eds.) ICCHP 2020. LNCS, vol. 12376, pp. 258–265. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58796-3_31

  18. Fernández Huerta, J.: Medidas sencillas de lecturabilidad. Consigna 214, 29–32 (1959)

    Google Scholar 

  19. Rello, L., Baeza-Yates, R., Dempere-Marco, L., Saggion, H.: Frequent words improve readability and short words improve understandability for people with dyslexia. In: Kotzé, P., Marsden, G., Lindgaard, G., Wesson, J., Winckler, M. (eds.) INTERACT 2013. LNCS, vol. 8120, pp. 203–219. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40498-6_15

    Chapter  Google Scholar 

Download references

Acknowledgements

This research has been partially funded by INSIGHT research project (PID2022-137344OB-C32) and the grant for research contracts PEJ-2021-AI/SAL-21563. We also thank Santiago Moreno Fernandez, Victor Muñoz-Velasco and Changao Wu for their support in the PLN analyzer.

Author information

Authors and Affiliations

  1. Department of Computer Science Carlos III, University of Madrid, 28911, Madrid, Leganes, Spain

    Andrea Sastre, Ana Iglesias & Jorge Morato

  2. Department of Library and Information Science, Complutense University of Madrid, 28018, Madrid, Spain

    Sonia Sanchez-Cuadrado

Authors
  1. Andrea Sastre
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ana Iglesias
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jorge Morato
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Sonia Sanchez-Cuadrado
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Andrea Sastre .

Editor information

Editors and Affiliations

  1. ISEG, Universidade de Lisboa, Lisbon, Portugal

    Álvaro Rocha

  2. College of Engineering, The Ohio State University, Columbus, OH, USA

    Hojjat Adeli

  3. Institute of Data Science and Digital Technologies, Vilnius University, Vilnius, Lithuania

    Gintautas Dzemyda

  4. DCT, Universidade Portucalense, Porto, Portugal

    Fernando Moreira

  5. Institute of Information Technology, Lodz University of Technology, Łódz, Poland

    Aneta Poniszewska-Marańda

Appendix I. Linguistic Elements Analyzed

Appendix I. Linguistic Elements Analyzed

Table 3 shows the comparative data in original text (O) and generated text (G) using ChatGPT system for the 10 texts extracted from the Spanish Government web pages. Boxed bold text is used to highlight when the generated text is worse than the recommendation.

Table 3. Recommendations and number of occurrences in each original and generated text.
Full size table

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Sastre, A., Iglesias, A., Morato, J., Sanchez-Cuadrado, S. (2024). Is ChatGPT Able to Generate Texts that Are Easy to Understand and Read?. In: Rocha, Á., Adeli, H., Dzemyda, G., Moreira, F., Poniszewska-Marańda, A. (eds) Good Practices and New Perspectives in Information Systems and Technologies. WorldCIST 2024. Lecture Notes in Networks and Systems, vol 987. Springer, Cham. https://doi.org/10.1007/978-3-031-60221-4_14

Download citation

Publish with us

Policies and ethics