English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

ChatGPT has the ability to generate grammatically flawless andseemingly-human replies to different types of questions from various domains.The number of its users and of its applications is growing at an unprecedentedrate. Unfortunately, use and abuse come hand in hand. In this paper, we studywhether a machine learning model can be effectively trained to accuratelydistinguish between original human and seemingly human (that is,ChatGPT-generated) text, especially when this text is short. Furthermore, weemploy an explainable artificial intelligence framework to gain insight intothe reasoning behind the model trained to differentiate betweenChatGPT-generated and human-generated text. The goal is to analyze model'sdecisions and determine if any specific patterns or characteristics can beidentified. Our study focuses on short online reviews, conducting twoexperiments comparing human-generated and ChatGPT-generated text. The firstexperiment involves ChatGPT text generated from custom queries, while thesecond experiment involves text generated by rephrasing originalhuman-generated reviews. We fine-tune a Transformer-based model and use it tomake predictions, which are then explained using SHAP. We compare our modelwith a perplexity score-based approach and find that disambiguation betweenhuman and ChatGPT-generated reviews is more challenging for the ML model whenusing rephrased text. However, our proposed approach still achieves an accuracyof 79%. Using explainability, we observe that ChatGPT's writing is polite,without specific details, using fancy and atypical vocabulary, impersonal, andtypically it does not express feelings.

ChatGPT or Human? Detect and Explain. Explaining Decisions of Machine Learning Model for Detecting Short ChatGPT-generated Text