• International Journal of Computer Science & Network Security
• /
• 제23권4호
• /
• pp.15-24
• /
• 2023

One of the objectives and aspirations of scientists and engineers ever since the development of computers has been to interact naturally with machines. Hence features of artificial intelligence (AI) like natural language processing and natural language generation were developed. The field of AI that is thought to be expanding the fastest is interactive conversational systems. Numerous businesses have created various Virtual Personal Assistants (VPAs) using these technologies, including Apple's Siri, Amazon's Alexa, and Google Assistant, among others. Even though many chatbots have been introduced through the years to diagnose or treat psychological disorders, we are yet to have a user-friendly chatbot available. A smart generative cognitive behavioral therapy with spoken dialogue systems support was then developed using a model Persona Perception (P2) bot with Generative Pre-trained Transformer-2 (GPT-2). The model was then implemented using modern technologies in VPAs like voice recognition, Natural Language Understanding (NLU), and text-to-speech. This system is a magnificent device to help with voice-based systems because it can have therapeutic discussions with the users utilizing text and vocal interactive user experience.

• Journal of Information Technology Applications and Management
• /
• 제31권3호
• /
• pp.149-163
• /
• 2024

As conversational AI systems such as ChatGPT have become more advanced, researchers are exploring ways to use them in education. However, we need effective ways to evaluate these systems before allowing them to help teach students. This study proposes a detailed framework for testing conversational AI across three important criteria as follow. First, specialized benchmarks that measure skills include giving clear explanations, adapting to context during long dialogues, and maintaining a consistent teaching personality. Second, adaptive standards check whether the systems meet the ethical requirements of privacy, fairness, and transparency. These standards are regularly updated to match societal expectations. Lastly, evaluations were conducted from three perspectives: technical accuracy on test datasets, performance during simulations with groups of virtual students, and feedback from real students and teachers using the system. This framework provides a robust methodology for identifying strengths and weaknesses of conversational AI before its deployment in schools. It emphasizes assessments tailored to the critical qualities of dialogic intelligence, user-centric metrics capturing real-world impact, and ethical alignment through participatory design. Responsible innovation by AI assistants requires evidence that they can enhance accessible, engaging, and personalized education without disrupting teaching effectiveness or student agency.

• 한국엔터테인먼트산업학회논문지
• /
• 제14권7호
• /
• pp.79-94
• /
• 2020

본 연구의 목적은 가상현실 스포츠 이용 활성화를 위한 프레즌스(Presence)이 참여만족(Participation Satisfaction)에 미치는 영향의 차이 분석하여 지속적으로 스크린골프 운동참여하도록 제시하고 가상현실 스포츠 시장 전반의 발전을 위한 실증적이고 학술적인 자료를 제공하는 것에 주된 목적이 있다. 이를 위해 조사기간은 2020년 3월 13일부터 5월 13일까지 5명의 연구진과 보조원으로 구성하였다. 연구의 목적과 설문에 대한 스크린 골프를 직접 경험한 소비자에게 충분한 설명을 한 후 자기평가기입법(self-administration method)으로 설문지를 작성하도록 하여 얻은 전체 247부의 설문지를 최종 유효표본으로 사용하였다. 자료처리방법으로는 통계 프로그램 Window SPSS 18.0프로그램을 이용하였다. 첫째, 요인분석과 신뢰도 분석, 둘째, 빈도분석 평균(M)과 표준편차(SD), 셋째, t-test와 One-way ANOVA 분석을 실시하였고 사후분석방법 중 쉐페(Scheffe)분석, 넷째, 변수들 간의 상관분석 및 다중회귀분석(Multiple Regression Analysis)을 실시하였다. 이와 같은 방법과 절차를 통하여 본 연구에서 얻어진 결과는 다음과 같다. 첫째, 일반적 특성의 성별, 참여기간에서 프레즌스이 참여만족에 유의한 차이가 나타났다. 둘째, 프레즌스의 하위요인 사회적 실재감, 사회적 주체감, 자아감은 참여만족 하위요인 사회적 만족, 심리적 만족, 신체적 만족에 높은 차이가 나타났다. 셋째, 프레즌스의 하위요인 사회적 실재감, 사회적 주체감, 자아감은 참여만족 하위요인 사회적 만족, 심리적 만족에 높은 영향이 미치는 것으로 나타났다.

• 인터넷정보학회논문지
• /
• 제16권3호
• /
• pp.33-41
• /
• 2015

본 논문에서는 디지털논리회로의 설계에 있어 필수적인 카르노 맵 간략화 과정을 교육용 자바 애플릿의 형태로 구현하였다. 학습자는 구현된 자바 애플릿으로부터 흥미로운 학습을 경험할 수 있으며, 자바 애플릿 설계과정에서 교육공학적인 요소를 단계별로 고려하였기 때문에 학습 효율의 극대화가 가능하다. 학습자는 구현된 자바 애플릿으로부터 디지털 논리회로의 간략화 과정을 마우스로 버튼을 클릭하거나 텍스트를 채워가면서 웹상에서 가상실험을 진행한다. 또한, 간략화 과정에서 발생되는 논리식과 논리회로도는 학습자가 효율적으로 학습할 수 있도록 서로 다른 프레임으로 구성하였으며, 학습자가 구성한 논리회로도가 올바르게 구성되었는지 확인할 수 있도록 하였다. 마지막으로 본 논문에서는 수정된 Quine-McCluskey 간략화 기법에 기초하여 자바 애플릿을 구현하였기 때문에 오프라인 교육의 보조도구로서 사용된다면 학습효율의 향상에 기여할 수 있다는 것을 입증하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권6호
• /
• pp.2049-2068
• /
• 2021

AI combined with NLP techniques has promoted the use of Virtual Assistants and have made people rely on them for many diverse uses. Conversational Agents are the most promising technique that assists computer users through their operation. An important challenge in developing Conversational Agents globally is transferring the groundbreaking expertise obtained in English to other languages. AI is making it possible to transfer this learning. There is a dire need to develop systems that understand secular languages. One such difficult language is Hindi, which is the fourth most spoken language in the world. Semantic similarity is an important part of Natural Language Processing, which involves applications such as ontology learning and information extraction, for developing conversational agents. Most of the research is concentrated on English and other European languages. This paper presents a Corpus-based word semantic similarity measure for Hindi. An experiment involving the translation of the English benchmark dataset to Hindi is performed, investigating the incorporation of the corpus, with human and machine similarity ratings. A significant correlation to the human intuition and the algorithm ratings has been calculated for analyzing the accuracy of the proposed similarity measures. The method can be adapted in various applications of word semantic similarity or module for any other language.

• 한국의류학회지
• /
• 제46권3호
• /
• pp.464-480
• /
• 2022

With the steady development of Artificial Intelligence (AI), online stores are adopting chatbot services as virtual shopping assistants. This study proposes the concept of para-social presence to explore the undiscovered role of fashion chatbots' emotional and relational characteristics on service acceptance. Based on the Technology Acceptance Model (TAM), this study investigates the effect of a chatbot's para-social presence on service acceptance intention through consumers' beliefs. The web-based experiment was conducted on adult consumers who experienced chatbot services in an online shopping situation. A total of 247 responses were analyzed using confirmatory factor analysis, structural equation modeling, and multi-group SEM by AMOS 21.0 and SPSS 23.0. The findings illustrate that the chatbot's intimacy positively influenced consumers' perceived enjoyment, while the chatbot's understanding had a significant effect on perceived usefulness and ease of use. The chatbot's involvement had a positive effect on all consumer beliefs. Moreover, perceived ease of use had a positive influence on usefulness. A greater level of perceived usefulness and enjoyment positively heightened consumers' service acceptance intention. This study also verifies the moderating role of a need for human interaction. Consumers with a high need for human interaction have a relatively low tendency to perceive chatbot services as useful.

• The Journal of Asian Finance, Economics and Business
• /
• 제9권5호
• /
• pp.519-529
• /
• 2022

Many consumers are opting for online booking over traditional booking systems. Customers can actively seek out information about hotels and lodging services, as well as book rooms, at any time and from any location. Customers also feel more supported when they interact with virtual assistants or professionals. Recognizing this issue, several hotels have focused on improving their websites by incorporating aspects that encourage customers to book directly through the hotel's website. The study's goal is to discover what factors impact people's decisions to book a hotel stay through the hotel's website. Therefore, hotel managers and owners can make decisions to improve the hotel website to attract residents to Can Tho City. The factors are website quality, affective commitment, social presence, and e-trust that affect customers' decision to book through the hotel website. The study uses quantitative methods to collect data from 180 residents living in Can Tho. Through data analysis on SPSS and Amos software, the research results show that three factors considered, namely website quality, affective commitment, and social presence, positively influence customers' booking decisions. This finding also suggests that e-trust is less critical to residents in Can Tho City, different from what the study had predicted.