Earticle

본 연구는 생성형 인공지능(Generative AI)인 ChatGPT의 등장 이후 Q&A 플랫폼에서 사용자 질문 행태가 어떻게 변화했는지 실증적으로 분석한다. 국내 최대 Q&A 플랫폼인 네이버 지식인의 IT/테크 카테고리 내 기능적 문제 해결에 해당하는 도구적 키워드(코딩, 파이썬, 자바, c언어)를 중심으로 ChatGPT 도입 전후의 질문 수 및 검색량 대비 질문 수 비율 변화를 분석하였다. 통제집단합성법과 이중차분법 분석을 통해 생성형 AI 도입 이후 도구적 키워드 질문 수가 감소하고 질문/검색 비율도 유의미하게 하락한 것으로 나타났다. 이는 사용자들이 구조화되고 기능적인 문제는 인간 답변보다는 생성형 AI 응답을 수용하는 경향을 보이며, Q&A 플랫폼 내 질문 행태가 변화하였음을 시사한다. 본 연구는 알고리즘 회피 이론에 기반하여 정보의 성격에 따라 AI 수용 여부가 달라지는 사용자 인식을 실증적으로 확인하였다. 이를 통해 생성형 AI 시대 디지털 지식 생태계의 구조 변화와 인간과 AI 상호작용 방식에 대한 이해를 확장한다.

This study empirically investigates how user questioning behavior on Q&A platforms has changed following the emergence of generative artificial intelligence (Generative AI), focused on ChatGPT. Focusing on the IT/Tech category of Naver Knowledge iN, we examine shifts in user behavior before and after the release of ChatGPT. The analysis investigates utilitarian keywords (coding, python, Java, C language) associated with functional problem solving. Employing a combination of the Synthetic Control Method and Difference-in-Differences analysis, we find a statistically significant decline in both the number of questions involving utilitarian keywords and the ratio of questions to searches following the adoption of generative AI. These findings suggest that users increasingly tend to accept AI-generated responses over human answers when faced with structured problem scenario. This indicates a shift in user questioning behavior within the Q&A platform. Based on the theory of algorithm aversion, this study empirically confirmed that user acceptance of AI is contingent on the characteristics of information. Therefore, it contributes to a deeper understanding of the structural transformation of the digital knowledge ecosystem and the evolving dynamics of human-AI interaction in the era of generative AI.

Considering production and marketing coordination between supply chain enterprises, this paper specifies a multi-agent supply chain concurrent negotiation model for two-stage supply chain in the supply chain environment. Coordinator is used to search optimal proposals based on particle swarm optimization (PSO) and send these proposals to other threads. Proposal strategies based on retention value and time are put forward by learning retention value of rivals through Parzen-window estimation. Simulation experiment is conducted to test negotiation performance of the model. Compared with ordinary models, the model makes two improvements as follows: (1)PSO is inserted into coordinator to improve negotiation efficiency; (2) Proposal strategies are effectively supported by Parzen-window estimation and enable agents to consider the retention values of rivals. Further researches need to be done to study trust relationship between agents and influence of external environment on supply chain negotiation solution.