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

In the first half of 2023, text-generative artificial intelligence (AI),including ChatGPT, equipped with GPT-3.5 and GPT-4, from OpenAI, has attractedconsiderable attention worldwide. In this study, first, we compared Japanesestylometric features of texts generated by GPT (-3.5 and -4) and those writtenby humans. In this work, we performed multi-dimensional scaling (MDS) toconfirm the distributions of 216 texts of three classes (72 academic paperswritten by 36 single authors, 72 texts generated by GPT-3.5, and 72 textsgenerated by GPT-4 on the basis of the titles of the aforementioned papers)focusing on the following stylometric features: (1) bigrams of parts-of-speech,(2) bigram of postpositional particle words, (3) positioning of commas, and (4)rate of function words. MDS revealed distinct distributions at each stylometricfeature of GPT (-3.5 and -4) and human. Although GPT-4 is more powerful thanGPT-3.5 because it has more parameters, both GPT (-3.5 and -4) distributionsare likely to overlap. These results indicate that although the number ofparameters may increase in the future, GPT-generated texts may not be close tothat written by humans in terms of stylometric features. Second, we verifiedthe classification performance of random forest (RF) for two classes (GPT andhuman) focusing on Japanese stylometric features. This study revealed the highperformance of RF in each stylometric feature: The RF classifier focusing onthe rate of function words achieved 98.1% accuracy. Furthermore the RFclassifier focusing on all stylometric features reached 100% in terms of allperformance indexes (accuracy, recall, precision, and F1 score). This studyconcluded that at this stage we human discriminate ChatGPT from human limitedto Japanese language.

Distinguishing ChatGPT(-3.5, -4)-generated and human-written papers through Japanese stylometric analysis