Prior to 2012 artificial intelligence, the study of intelligent agents, followed Moore’s law which states that compute is doubling every two years. Post 2012 it has been doubling every 3.4 months. However, intelligent agents are focusing on human language, and conversation is rarely developed for education. This study investigates a student’s perceived benefits and limitations of chatbots in higher education, by exploring the relative advantage, complexity, and compatibility of a different chatbot functionality. By interviewing students the authors could establish four different themes that perceived to be important when using a chatbot, Decreasing obstacles, Enhanced learning process, Hesitance towards complexity, and Teacher involvement. Overall, this study suggests that it is preferable to start with little functionality and then successively improve. Because smaller implementations with basic functionality are more accepted and useful to students compared to complex AI functionality, and for future implementation, this is something that should be accounted for. / Före 2012 följde Artificiell intelligens, läran om intelligenta agenter Moores lag vilket innebär att data beräkningars kraft fördubblas vartannat år. Efter 2012 har det fördubblats var 3,4 månad. Dock utvecklas ofta de intelligenta agenterna med fokus på det mänskliga språket samt hälsa och sällan för utbildnings syfte. Den här studien undersöker studenters uppfattning om fördelar och nackdelar av chatbotar i högre utbildningssyfte genom att utforska relativa fördelar, svårigheter och kompatibiliteten av olika chatbot funktionaliteter. Genom att intervjua studenter kunde författarna etablera fyra olika teman som uppfattades vara viktiga när en chatbot används, att minska hinder, förbättra lärningsprocessen, tvivel gentemot svårigheter och lärarens medverkan. Sammanfattningsvis pekar denna studie på att det är att föredra att börja utveckla chatbotar med med lite funktionalitet och att sedan successivt öka. Detta för att mindre implementationer med grundlig funktionalitet är mer accepterad och användbar för studenter jämfört med komplex AI funktionalitet, och detta är något att ta hänsyn till i framtida implementationer.

This project investigates the intersection between reflection through journaling and Artificial Intelligence (AI), more specifically Conversational Agents (CA) in interaction design. Journaling together with a CA is a relatively unexplored area in HCI and Interaction Design, especially when studying the experiential aspect. Furthermore, designing for reflection has been a rising topic within HCI and Interaction Design. The project used a modified version of the double diamond model as a design process to research, create and test a concept for multimodal interactive journaling using a conversational agent. The results suggest that conversational agents have the potential to play an influential and positive role in evoking reflection in an individual through collaborative and conversational interaction. The project provides design recommendations for designing an interactive journaling experience with a conversational agent and an example of how designers can design using interaction, AI, and language as a design material. The project contributes insights to designing artifacts for reflection and how a design process can be designed to design for AI and conversational interfaces.

As Digital Personal Assistants get increasingly present in our lives, repositioning Conversational Interfaces within Interaction Design could be beneficial. More contributions seem possible beyond the commercial vision of Conversational Agents as digital assistants. In this thesis, Design fiction is adopted as an approach to explore a future for these technologies, focusing on the possible social and ritual practices that might arise when Conversational Agents and Artificial Intelligence are employed in contexts such as mortality and grief. As a secondary but related concern, it is argued that designers need to come to find ways to work with Artificial Intelligence and Machine Learning, uncovering the “AI blackbox”, and understanding its basic functioning, therefore, Machine learning is explored as a design material. This research through design project presents a scenario where the data we leave behind us are used after we die to build conversational models that become digital altars, shaping the way we deal with grief and death. This is presented through a semi-functional prototype and a diegetic prototype in the form of a short video.

Les Agents Conversationnels Animés sont des personnages virtuels dont la fonction principale est d'interagir avec l'utilisateur. Ils sont utilisés dans différents domaines tels que l'assistance personnelle, l'entrainement social ou les jeux vidéo et afin d'améliorer leur potentiel, il est possible de leur donner la capacité d'exprimer des comportements similaires à ceux des humains. Les utilisateurs, conscient d'interagir avec une machine, sont tout de même capable d'analyser et d'identifier des comportements sociaux à travers les signaux émis par les agents. La recherche en ACA s'est longtemps intéressée aux mécanismes de reproduction et de reconnaissance des émotions au sein de ces personnages virtuels et maintenant l'intérêt se porte sur la capacité d'exprimer différentes attitudes sociales. Ces attitudes reflètent un style comportemental et s'expriment à travers différentes modalités du corps comme les expressions faciales, les regards ou les gestes par exemple. Nous avons proposé un modèle permettant à un agent de produire différents comportements non-verbaux traduisant l'expression d'attitudes sociales dans une conversation. L'ensemble des comportements générés par notre modèle permettent à un groupe d'agents animés par celui-ci de simuler une conversation, sans tenir compte du contenu verbal. Deux évaluations du modèle ont été conduites, l'une sur Internet et l'autre dans un environnement de réalité virtuelle, afin de vérifier que les attitudes étaient bien reconnues. / Embodied Conversational Agents are virtual characters which main purpose is to interact with a human user. They are used in various domains such as personal assistance, social training or video games for instance. In order to improve their capabilities, it is possible to give them the ability to produce human-like behaviors. The users, even if they are aware that they interact with a machine, are still capable of analyzing and identifying social behaviors through the signals produced by these virtual characters. The research in Embodied Conversational Agents has focused for a long time on the reproduction and recognition of emotions by virtual characters and now the focus is on the ability to express different social attitudes. These attitudes show a behavioral style and are expressed through different modalities of the body, like the facial expressions, the gestures or the gazes for instance. We proposed a model that allows an agent to produce different nonverbal behaviors expressing different social attitudes in a conversation. The whole set of behaviors produced by our model allows a goup of agents animated by it to simulate a conversation, without any verbal content. Two evaluations of the model were conducted, one on the Internet and one in a Virtual Reality environment, to verify that the attitudes produced are well recognized

Les agents virtuels conversationnels ayant un comportement social reposent souvent sur au moins deux disciplines différentes : l’informatique et la psychologie. Dans la plupart des cas, les théories psychologiques sont converties en un modèle informatique afin de permettre aux agents d’adopter des comportements crédibles. Nos travaux de thèse se positionnent au croisement de ces deux champs disciplinaires. Notre objectif est de renforcer la crédibilité des agents conversationnels. Nous nous intéressons aux agents conversationnels orientés tâche, qui sont utilisés dans un contexte professionnel pour produire des réponses à partir d’une base de connaissances métier. Nous proposons un modèle affectif pour ces agents qui s’inspire des mécanismes affectifs chez l’humain. L’approche que nous avons choisie de mettre en œuvre dans notre modèle s’appuie sur la théorie des Tendances à l’Action en psychologie. Nous avons proposé un modèle des émotions en utilisant un formalisme inspiré de la logique BDI pour représenter les croyances et les buts de l’agent. Ce modèle a été implémenté dans une architecture d’agent conversationnel développée au sein de l’entreprise DAVI. Afin de confirmer la pertinence de notre approche, nous avons réalisé plusieurs études expérimentales. La première porte sur l’évaluation d’expressions verbales de la tendance à l’action. La deuxième porte sur l’impact des différentes stratégies de régulation possibles sur la perception de l’agent par l’utilisateur. Enfin, la troisième étude porte sur l’évaluation des agents affectifs en interaction avec des participants. Nous montrons que le processus de régulation que nous avons implémenté permet d’augmenter la crédibilité et le professionnalisme perçu des agents, et plus généralement qu’ils améliorent l’interaction. Nos résultats mettent ainsi en avant la nécessité de prendre en considération les deux mécanismes émotionnels complémentaires : la génération et la régulation des réponses émotionnelles. Ils ouvrent des perspectives sur les différentes manières de gérer les émotions et leur impact sur la perception de l’agent. / Conversational virtual agents with social behavior are often based on at least two different disciplines : computer science and psychology. In most cases, psychological findings are converted into computational mechanisms in order to make agents look and behave in a believable manner. In this work, we aim at increasing conversational agents’ belivielibity and making human-agent interaction more natural by modelling emotions. More precisely, we are interested in task-oriented conversational agents, which are used as a custumer-relationship channel to respond to users request. We propose an affective model of emotional responses’ generation and control during a task-oriented interaction. Our proposed model is based, on one hand, on the theory of Action Tendencies (AT) in psychology to generate emotional responses during the interaction. On the other hand, the emotional control mechanism is inspired from social emotion regulation in empirical psychology. Both mechanisms use agent’s goals, beliefs and ideals. This model has been implemented in an agent architecture endowed with a natural language processing engine developed by the company DAVI. In order to confirm the relevance of our approach, we realized several experimental studies. The first was about validating verbal expressions of action tendency in a human-agent dialogue. In the second, we studied the impact of different emotional regulation strategies on the agent perception by the user. This study allowed us to design a social regulation algorithm based on theoretical and empirical findings. Finally, the third study focuses on the evaluation of emotional agents in real-time interactions. Our results show that the regulation process contributes in increasing the credibility and perceived competence of agents as well as in improving the interaction. Our results highlight the need to take into consideration of the two complementary emotional mechanisms : the generation and regulation of emotional responses. They open perspectives on different ways of managing emotions and their impact on the perception of the agent.

京都大学 / 0048 / 新制・課程博士 / 博士(情報学) / 甲第17925号 / 情博第507号 / 新制||情||90(附属図書館) / 30745 / 京都大学大学院情報学研究科知能情報学専攻 / (主査)教授 西田 豊明, 教授 河原 達也, 教授 黒橋 禎夫 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DGAM

No description available.

This study focuses on evaluating and enhancing the user experience of Emely, a conversational agent aimed at improving language skills for second language learners, particularly those who want to increase their chances of securing employment in Sweden. Usability testing was conducted in two test rounds, with the first round providing design implications for the user interface in the second round. However, assessing the effectiveness of the interface improvements was challenging due to low Swedish proficiency among the test groups consisting of potential users of Emely. Although the study did not result in design implications for the user interface, important findings highlight the need to adapt conversational agents, like Emely, for users with low literacy levels and illiteracy, emphasizing the importance of inclusive design for effective language learning support.

The success of software development projects heavily depends on effectively capturing and meeting stakeholders' requirements. However, involving multiple stakeholders with diverse backgrounds and objectives often leads to conflicts among these requirements. These conflicts represent inconsistencies in the system design, resulting in various challenges, including project delays, increased costs, and potential system failures. Previous research has primarily focused on identifying conflicts with algorithms or negotiation, while conversational AI's potential to detect conflicts in real-time has been neglected. This thesis study addresses the challenge of requirement conflicts by proposing a novel approach that leverages conversational AI in the form of a chatbot. The chatbot, developed using the Rasa platform, enables real-time detection of conflicts, focusing on three general types: duplicated (similar), incompatible, and contradictory requirements. During the study, the design science research method is employed to guide the chatbot's development. Further, an experiment is applied to evaluate the chatbot's performance compared with domain experts using four different datasets. The experiment results are presented using F1 scores, which calculate precision and recall for both the chatbot and the experts on each dataset. Overall, the chatbot scored 0.8, while the experts achieved a slightly higher score of 0.86. To determine if there was a statistically significant difference between the two performances, a Wilcoxon signed-rank test was conducted on the results. The analysis showed no significant difference in the F1 score between the chatbot and the experts, indicating the chatbot's feasibility and effectiveness in detecting conflicts. The contribution of this thesis study can advance requirements engineering by providing a user-friendly and efficient method for real-time conflict detection, enhancing the quality and overall success of software development projects.

This thesis investigates the impact of the voice modality on user trust in conversational chatbot interfaces. The assumption is that trust can be increased by adding voice output to a chatbot and by a higher quality of a used text-to-speech synthesis. The thesis first introduces chatbots and the concept of conversational interfaces then defines trust in an online context. Based on this, a model for trust and perceiving factors for credibility, ease of use and risk is defined. An online experiment is conducted where participants run through conversational scenarios with a chatbot while varying the voice output. Followed by a survey to collect data about the perception of the trust factors for a scenario with no voice and two scenarios with different speech synthesis qualities. To analyse the ordinal data from the survey the ”Wilcoxon signed- rank test”, a nonparametric statistical test, is conducted to compare trust for the voice output types. Results show that adding the voice output modality to a conversational chatbot interface increases the user trust towards the service. Furthermore, the assumption that synthesis quality has an effect on trust could not hold true because the results are not statistically significant. On this basis, the limitations of the used methods are discussed and suggestions for further research are proposed. / Detta examensarbete undersöker den inverkan som röstmodaliteten har på användarförtroende i konversationsbaserade gränssnitt för chatbottar. Antagandet är att förtroendet kan ökas, dels genom att addera röstutmatning till chatbotten och dels genom att text-till-röst-syntesen ges hög kvalité. Först introduceras chatbottar och konceptet konversationsbaserade gränssnitt. Därefter definieras örtroende i en online-kontext. Baserat på detta definieras en modell för förtroende samt uppfattningsfaktorer för trovärdighet, lättanvändhet och risk. Ett onlineexperiment utfördes, där deltagare går igenom konversationscenarion med en chatbot medan röstutmatningen varieras. Därefter följde en undersökning ämnad att samla in data om uppfattningen om förtroendefaktorerna för ett scenario utan röst och två scenarion med olika talsyntes-kvalitéer. För att analysera den ordnade datan från undersökningen genomfördes Wilcoxon signedrank-testet, ett ickeparametriskt statistiskt test, för att jämföra förtroenden för de olika röstutmatningstyperna. Resultaten visar att addering av röstutmatningsmodalitet till ett konversationsbaserat chatbotsgränsnitt ökar användares förtroende för tjänsten. Vidare, antagandet att synteskvalitén har effekt på förtroendet kunde inte verifieras därför att resultaten inte är statistiskt signifikanta. Begränsningarna hos de använda metoderna diskuteras och förslag för framtida forskning läggs fram.