IDEAS home Printed from https://ideas.repec.org/a/eee/tefoso/v189y2023ics0040162523000653.html
   My bibliography  Save this article

Efficiency of automatic text generators for online review content generation

Author

Listed:
  • Perez-Castro, A.
  • Martínez-Torres, M.R.
  • Toral, S.L.

Abstract

The evolution of Artificial Intelligence has led to the appearance of automatic text generators able to closely resemble human writing, endangering the development of e-commerce and the consumer confidence. Thus, it is critical to deeply understand how these text generators work to present the presence of deceptive reviews. This paper analyzes one of the most popular text generators, GPT2 (Generative Pre-trained Transformer 2), and studies its effectivity compared to human-generated reviews using previously published classifiers trained to distinguish between real and deceptive reviews. One parameter of the model is the so-called temperature, which determines how deterministic the model is. The temperature adjusts the probability distribution of the words in the model, so that a higher temperature translates into a higher degree of inventiveness in the generation of the texts. Findings reveal (i) that automatically-generated deceptive reviews worsen the accuracy of existing classifiers, this effect being accentuated by the degree of inventiveness; (ii) that their performance depends on the data used to train the generator; and (iii) that the sentiment polarity has no effect on the performance of detection classifiers.

Suggested Citation

  • Perez-Castro, A. & Martínez-Torres, M.R. & Toral, S.L., 2023. "Efficiency of automatic text generators for online review content generation," Technological Forecasting and Social Change, Elsevier, vol. 189(C).
    • Handle: RePEc:eee:tefoso:v:189:y:2023:i:c:s0040162523000653
    DOI: 10.1016/j.techfore.2023.122380
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0040162523000653
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.techfore.2023.122380?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Salminen, Joni & Kandpal, Chandrashekhar & Kamel, Ahmed Mohamed & Jung, Soon-gyo & Jansen, Bernard J., 2022. "Creating and detecting fake reviews of online products," Journal of Retailing and Consumer Services, Elsevier, vol. 64(C).
    2. Filieri, Raffaele & Alguezaui, Salma & McLeay, Fraser, 2015. "Why do travelers trust TripAdvisor? Antecedents of trust towards consumer-generated media and its influence on recommendation adoption and word of mouth," Tourism Management, Elsevier, vol. 51(C), pages 174-185.
    3. Choi, Seokkyu & Lee, Hyeonju & Park, Eunjeong & Choi, Sungchul, 2022. "Deep learning for patent landscaping using transformer and graph embedding," Technological Forecasting and Social Change, Elsevier, vol. 175(C).
    4. Chung, Park & Sohn, So Young, 2020. "Early detection of valuable patents using a deep learning model: Case of semiconductor industry," Technological Forecasting and Social Change, Elsevier, vol. 158(C).
    5. Zhou, Shuang & Barnes, Liz & McCormick, Helen & Blazquez Cano, Marta, 2021. "Social media influencers’ narrative strategies to create eWOM: A theoretical contribution," International Journal of Information Management, Elsevier, vol. 59(C).
    6. Petrescu, Maria & O’Leary, Kathleen & Goldring, Deborah & Ben Mrad, Selima, 2018. "Incentivized reviews: Promising the moon for a few stars," Journal of Retailing and Consumer Services, Elsevier, vol. 41(C), pages 288-295.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Ben Jabeur, Sami & Ballouk, Hossein & Ben Arfi, Wissal & Sahut, Jean-Michel, 2023. "Artificial intelligence applications in fake review detection: Bibliometric analysis and future avenues for research," Journal of Business Research, Elsevier, vol. 158(C).
    2. Wang, Zheng & Wang, Lun & Ji, Ying & Zuo, Lulu & Qu, Shaojian, 2022. "A novel data-driven weighted sentiment analysis based on information entropy for perceived satisfaction," Journal of Retailing and Consumer Services, Elsevier, vol. 68(C).
    3. Perez, Dikla & Stockheim, Inbal & Baratz, Guy, 2022. "Complimentary competition: The impact of positive competitor reviews on review credibility and consumer purchase intentions," Journal of Retailing and Consumer Services, Elsevier, vol. 69(C).
    4. Tavakoli, Rokhshad & Mura, Paolo, 2018. "Netnography in tourism – Beyond Web 2.0," Annals of Tourism Research, Elsevier, vol. 73(C), pages 190-192.
    5. Perez-Vega, Rodrigo & Hopkinson, Paul & Singhal, Aishwarya & Mariani, Marcello M., 2022. "From CRM to social CRM: A bibliometric review and research agenda for consumer research," Journal of Business Research, Elsevier, vol. 151(C), pages 1-16.
    6. Román, Sergio & Riquelme, Isabel P. & Iacobucci, Dawn, 2023. "Fake or credible? Antecedents and consequences of perceived credibility in exaggerated online reviews," Journal of Business Research, Elsevier, vol. 156(C).
    7. Azer, Jaylan & Anker, Thomas & Taheri, Babak & Tinsley, Ross, 2023. "Consumer-Driven racial stigmatization: The moderating role of race in online consumer-to-consumer reviews," Journal of Business Research, Elsevier, vol. 157(C).
    8. Josef Zelenka & Tracy Azubuike & Martina Pásková, 2021. "Trust Model for Online Reviews of Tourism Services and Evaluation of Destinations," Administrative Sciences, MDPI, vol. 11(2), pages 1-21, March.
    9. Christina Katsikari & Leonidas Hatzithomas & Thomas Fotiadis & Dimitrios Folinas, 2020. "Push and Pull Travel Motivation: Segmentation of the Greek Market for Social Media Marketing in Tourism," Sustainability, MDPI, vol. 12(11), pages 1-18, June.
    10. José Alberto Martínez-González & Eduardo Parra-López & Almudena Barrientos-Báez, 2021. "Young Consumers’ Intention to Participate in the Sharing Economy: An Integrated Model," Sustainability, MDPI, vol. 13(1), pages 1-21, January.
    11. Koc, Erdogan & Hatipoglu, Sercan & Kivrak, Oguzhan & Celik, Cemal & Koc, Kaan, 2023. "Houston, we have a problem!: The use of ChatGPT in responding to customer complaints," Technology in Society, Elsevier, vol. 74(C).
    12. Rae Yule Kim, 2020. "The influx of skeptics: an investigation of the diffusion cycle effect on online review," Electronic Markets, Springer;IIM University of St. Gallen, vol. 30(4), pages 821-835, December.
    13. Charitha Harshani Perera & Rajkishore Nayak & Long Thang Van Nguyen, 2019. "Role of social word-of-mouth on emotional brand attachment and brand choice intention: A study on private educational institutes in Vietnam," Proceedings of Business and Management Conferences 8611115, International Institute of Social and Economic Sciences.
    14. Alamoudi, Hawazen & Shaikh, Aijaz A. & Alharthi, Majed & Dash, Ganesh, 2023. "With great power comes great responsibilities – Examining platform-based mechanisms and institutional trust in rideshare services," Journal of Retailing and Consumer Services, Elsevier, vol. 73(C).
    15. Carolina Aldao & Tanja A. Mihalic, 2020. "New Frontiers in Travel Motivation and Social Media: The Case of Longyearbyen, the High Arctic," Sustainability, MDPI, vol. 12(15), pages 1-18, July.
    16. Čaušević Amra & Fusté-Forné Francesc, 2022. "Local Cuisine in a Tourist City: Food Identity in Sarajevo Restaurant Menus as a Source of Destination Marketing," European Journal of Tourism, Hospitality and Recreation, Sciendo, vol. 12(1), pages 61-77, December.
    17. Wen Zhang & Qiang Wang & Jian Li & Zhenzhong Ma & Gokul Bhandari & Rui Peng, 2023. "What makes deceptive online reviews? A linguistic analysis perspective," Palgrave Communications, Palgrave Macmillan, vol. 10(1), pages 1-14, December.
    18. Pantea Foroudi & Maria Palazzo & Karanikosova Sabina, 2023. "When Love Takes Over: Boosting Love Towards Airbnb Brand," Corporate Reputation Review, Palgrave Macmillan, vol. 26(4), pages 264-278, November.
    19. Kim, Juram & Hong, Suckwon & Kang, Yubin & Lee, Changyong, 2023. "Domain-specific valuation of university technologies using bibliometrics, Jonckheere–Terpstra tests, and data envelopment analysis," Technovation, Elsevier, vol. 122(C).
    20. Marwa Ghanem & Ibrahim Elshaer & Alaa Shaker, 2020. "The Successful Adoption of IS in the Tourism Public Sector: The Mediating Effect of Employees’ Trust," Sustainability, MDPI, vol. 12(9), pages 1-18, May.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:tefoso:v:189:y:2023:i:c:s0040162523000653. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.sciencedirect.com/science/journal/00401625 .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.