Can we spot fake public comments generated by ChatGPT(-3.5, -4)?: Japanese stylometric analysis expose emulation created by one-shot learning.

Public comments are an important opinion for civic when the government establishes rules. However, recent AI can easily generate large quantities of disinformation, including fake public comments. We attempted to distinguish between human public comments and ChatGPT-generated public comments (including ChatGPT emulated that of humans) using Japanese stylometric analysis. Study 1 conducted multidimensional scaling (MDS) to compare 500 texts of five classes: Human public comments, GPT-3.5 and GPT-4 generated public comments only by presenting the titles of human public comments (i.e., zero-shot learning, GPTzero), GPT-3.5 and GPT-4 emulated by presenting sentences of human public comments and instructing to emulate that (i.e., one-shot learning, GPTone). The MDS results showed that the Japanese stylometric features of the public comments were completely different from those of the GPTzero-generated texts. Moreover, GPTone-generated public comments were closer to those of humans than those generated by GPTzero. In Study 2, the performance levels of the random forest (RF) classifier for distinguishing three classes (human, GPTzero, and GPTone texts). RF classifiers showed the best precision for the human public comments of approximately 90%, and the best precision for the fake public comments generated by GPT (GPTzero and GPTone) was 99.5% by focusing on integrated next writing style features: phrase patterns, parts-of-speech (POS) bigram and trigram, and function words. Therefore, the current study concluded that we could discriminate between GPT-generated fake public comments and those written by humans at the present time.

Exploring the effects of COVID-19 on motorcycle riding patterns and its importance.

A motorcycle refers to a two-wheeled, personal mobility vehicle used for daily transportation and leisure activities. Leisure enables social interaction, and motorcycle riding could be an activity that facilitates social interactions and distancing. Therefore, grasping the importance of riding motorcycles during the pandemic-which involved social distancing and limited leisure activities-can be valuable. However, researchers have yet to examine its potential importance during the pandemic. Therefore, this study aimed to determine the importance of personal space and time spent with others in the context of motorcycle riding during the COVID-19 pandemic. We specifically explored the effects of COVID-19 on riding patterns and importance of riding motorcycle by examining whether these factors differed regarding changes in the frequency of motorcycle riding before and during the pandemic in daily and leisure-oriented transportation. Data were collected from 1,800 motorcycle users in Japan using a web-based survey conducted in November 2021. Respondents replied to questions concerning the importance of personal space and time spent with others attributed to motorcycle riding before and during the pandemic. Following the survey, we conducted a two-way repeated measures analysis of variance (two-factor ANOVA) and performed a simple main effect analysis using the SPSS syntax editor in case of interactions. The valid samples for motorcyclists with leisure motive (leisure-oriented users) and daily transportation motive (daily users) numbered n = 890 and n = 870, respectively (total n = 1,760, 95.5%). Each valid sample was divided into three groups based on the differences in motorcycle riding frequency before and during the pandemic: unchanged, increased frequency, and decreased frequency. The two-factor ANOVA results showed significant differences in the interaction effects for leisure-oriented and daily users regarding personal space and time spent with others. The mean value of the "increased frequency" group during the pandemic indicated significantly higher importance of personal space and time spent with others than the other groups. Motorcycle riding could enable daily transportation and leisure-oriented users to practice social distancing while simultaneously spending time with companions and alleviating loneliness and isolation during the pandemic.