Diese Arbeit beschäftigt sich mit der Erstellung und Evaluation eines E-Mentoring Systems auf Basis eines Chatbots in der Hochschullehre. Innerhalb des Verbundprojekts tech4comp und dessen zugrundeliegender technischer Infrastruktur ist ein erster Chatbot zur Unterstützung der digitalen Lehre implementiert worden. Dieser Bot hat die Aufgabe, anhand von Aufgabenempfehlungen den Lernerfolg zu steigern. In einer Studie mit Lernenden eines Mathematikmoduls an der Hochschule für Technik, Wirtschaft und Kultur Leipzig (HTWK) hat eine erste Evaluation stattgefunden. Mit den gesammelten Erfahrungswerten und dem detektierten Verbesserungspotenzial ist daraufhin ein Expertensystem mit auf Lerndaten basierenden Empfehlungsfunktionen realisiert worden. Die Arbeit zeigt das erfolgreiche Zusammenspiel verschiedener Komponenten innerhalb des Verbundprojekts. Gleichzeitig wird damit die Grundlage für weitere Entwicklungen innerhalb des E-Mentorings gelegt. Ergänzend dazu sind die Entwicklungspotenziale und die nächsten Schritte aufgezeigt, welche notwendig sind, um in Zukunft die Hochschullehre mittels selbstlernender künstlicher Intelligenz zu unterstützen.:1 Einleitung 2 Wissenschaftliche Grundlagen 2.1 Mentoring 2.1.1 Allgemein-pädagogische Perspektive 2.1.2 Inhaltliche Perspektive 2.1.3 Systemische Perspektive 2.1.4 E-Mentoring 2.2 Einordnung des Projekts 2.2.1 Verbundprojekt tech4comp 2.2.2 Bestehende Projekte 2.3 Chatbots 2.3.1 Historische Entwicklung 2.3.2 Chatbots in der Hochschullehre 2.4 Grundlagenmodellierung 2.4.1 Domänenmodellierung mittels einer Ontologie 2.4.2 Lernendenmodellierung 3 Technische Analyse der bestehenden Infrastruktur 3.1 Technische Gesamtinfrastruktur des Bildungsnetzwerks 3.2 Social Bot Framework 3.3 Rocket.Chat 3.4 Datenspeicher - Learning Record Store 3.5 Mentoring Workbench 3.6 KI-Infrastruktur 3.7 Lernmanagementsystem OPAL 3.8 ONYX-Aufgabeneditor 3.9 Authentifizierung 4 Umsetzung 4.1 Vorgehensweise 4.2 Aufbereitung der Lerninhalte 4.3 Erstellung der Ontologie 4.3.1 Überblick 4.3.2 Modellierung der Lernobjekte 4.4 Entwicklung des Chatbots und Durchführung der Studie 4.4.1 Entwicklung des Chatbots 4.4.2 Vorbereitungen im OPAL-Kurs 4.4.3 Datenschutzerklärung 4.4.4 Anleitung für die Studierenden 4.4.5 Auswertung der Studie 4.5 Entwicklung des dynamischen Expertensystems 4.5.1 Aufbereitung der Daten zur weiteren Nutzung 4.5.2 Entwicklung des KI-Service 5 Schlussbetrachtungen 5.1 Ausblick 5.1.1 Entwicklungen außerhalb der Chat-Interaktionen 5.1.2 Entwicklungen innerhalb der Chat-Interaktionen 5.1.3 Anpassungen der Aufgaben 5.2 Fazit Abbildungsverzeichnis Tabellenverzeichnis Quelltextverzeichnis Literaturverzeichnis Eidesstattliche Erklärung Anhang / This master thesis is about the creation and evaluation of an e-mentoring system based on a chatbot in higher education. In a first approach, a chatbot was used to support the students. The entire technical infrastructure and knowledge was shared as part of the tech4comp joint project. The primary objective is the recommendation of tasks for an increased learning experience. To get first feedback on the system, a study with students in a math class at the HTWK is conducted. Based on the results, an expert system got implemented and developed. In addition, the recommendation functions work with newly generated data from the students. This thesis shows the cooperation between different parts of the joint project. Moreover, it serves as a basis for further developments and studies in the field of e-mentoring. With the help of the implemented system, it is possible to gain insights into further potentials. The next iteration should include self-learning artificial intelligence to improve the bot’s suggestions.:1 Einleitung 2 Wissenschaftliche Grundlagen 2.1 Mentoring 2.1.1 Allgemein-pädagogische Perspektive 2.1.2 Inhaltliche Perspektive 2.1.3 Systemische Perspektive 2.1.4 E-Mentoring 2.2 Einordnung des Projekts 2.2.1 Verbundprojekt tech4comp 2.2.2 Bestehende Projekte 2.3 Chatbots 2.3.1 Historische Entwicklung 2.3.2 Chatbots in der Hochschullehre 2.4 Grundlagenmodellierung 2.4.1 Domänenmodellierung mittels einer Ontologie 2.4.2 Lernendenmodellierung 3 Technische Analyse der bestehenden Infrastruktur 3.1 Technische Gesamtinfrastruktur des Bildungsnetzwerks 3.2 Social Bot Framework 3.3 Rocket.Chat 3.4 Datenspeicher - Learning Record Store 3.5 Mentoring Workbench 3.6 KI-Infrastruktur 3.7 Lernmanagementsystem OPAL 3.8 ONYX-Aufgabeneditor 3.9 Authentifizierung 4 Umsetzung 4.1 Vorgehensweise 4.2 Aufbereitung der Lerninhalte 4.3 Erstellung der Ontologie 4.3.1 Überblick 4.3.2 Modellierung der Lernobjekte 4.4 Entwicklung des Chatbots und Durchführung der Studie 4.4.1 Entwicklung des Chatbots 4.4.2 Vorbereitungen im OPAL-Kurs 4.4.3 Datenschutzerklärung 4.4.4 Anleitung für die Studierenden 4.4.5 Auswertung der Studie 4.5 Entwicklung des dynamischen Expertensystems 4.5.1 Aufbereitung der Daten zur weiteren Nutzung 4.5.2 Entwicklung des KI-Service 5 Schlussbetrachtungen 5.1 Ausblick 5.1.1 Entwicklungen außerhalb der Chat-Interaktionen 5.1.2 Entwicklungen innerhalb der Chat-Interaktionen 5.1.3 Anpassungen der Aufgaben 5.2 Fazit Abbildungsverzeichnis Tabellenverzeichnis Quelltextverzeichnis Literaturverzeichnis Eidesstattliche Erklärung Anhang

In this thesis some ethical dilemmas involving conversational agents, with ChatGPT as the foremost example, are presented. Initially, the technology supporting chatbots is described to enable the reader to get insights into their underlying structure.  The reader will get an account of recent progress in the development of the technology and gain knowledge of ethical dilemmas from a developer’s perspective. The main goal of this literature study is to achieve an understanding of the current situation and reflect on the developer’s responsibility for buildingethical chatbots. The content of this thesis is further based on previous research in the scientific field of chatbots.  This literature study supports the developer with multiple advice. For example, the importance of working with areas such as transparency, UI-design, reliability, accountability, and relativization is highlighted. / I den här litteraturstudien presenteras etiska frågor gällande ”conversational agents” och den senaste tidens utveckling av ChatGPT kommer att stå i centrum för studien. Läsaren får först ta del av en allmän beskrivning av tekniken som ligger till grund för AI-baserade ”chatbots”. Jag redogör för den senaste tidens tekniska utveckling på området samt presentera etiska frågeställningar från programmerarens perspektiv. Det huvudsakliga syftet med uppsatsen är att förmedla en förståelse för den nuvarande situationen och reflektera över utvecklarens ansvar när det kommer till att skapa etiska ”chatbots”. Tidigare forskning om ”conversational agents” står som en grund för reflektioner och diskussioner i den här uppsatsen.  Den här litteraturstudien avslutas med flertalet slutsatser som kan fungera som råd till utvecklare. Programmerare bör uppmärksamma frågor som rör transparens, redovisningsansvar och relativisering. Dessutom är det viktigt att ta hänsyn till aspekter som UI-design och reliabilitet.

People interact through language and conversation everyday, children learn from an early age to express a variety of intents and responses in an understandable way. But the interaction form most commonly used in systems today is nothing like this. Instead, it is dominated by interactions such as button presses, scrolling, drag and drop, swipe gestures etc. What benefits and drawbacks can be observed when transforming such an application to one where users can use their natural inclination towards conversation to converse directly with the system. This exploratory study compares the usability of a conversational interaction form against the 'de facto'-standard that has a point and click interface. To assess usability differences, a chatbot prototype was designed and implemented. The prototype was developed in partnership with the consulting company Knowit and one of the leading Swedish clothing retailers. This prototype was subsequently tested against the clothing retailer's current application. The two interaction strategies were compared for usability for first and second time use. The results show some self reported usability differences in second time use favouring the chatbot prototype.

With the rising popularity of chatbots, not just in entertainment but in e-commerce and online chat support, it’s become increasingly important to be able to quickly set up chatbots that can respond to simple questions. This study examines which of two algorithms for automatic generation of chatbot knowledge bases, First Word Search or Most Significant Word Search, is able to generate the responses that are the most relevant to the topic of a question. It also examines how text corpora might be used as a source from which to generate chatbot knowledge bases. Two chatbots were developed for this project, one for each of the two algorithms that are to be examined. The chatbots are evaluated through a survey where the participants are asked to choose which of the algorithms they thought chose the response that was most relevant to a question. Based on the survey we conclude that Most Significant Word Search is the algorithm that picks the most relevant responses. Most Significant Word Search has a significantly higher chance of generating a response that is relevant to the topic. However, how well a text corpus works as a source for knowledge bases depends entirely on the quality and nature of the corpus. A corpus consisting of written dialogue is likely more suitable for conversion into a knowledge base.

Chatbots are software agents that interact with the user in a conversation. The main goal of their creation was to resemble a human being in the way they perform said interaction, trying to make the user think he/she is writing to another human being. This has been implemented with varying degrees of success. One of the most popular languages for the definition of a chatbot knowledge base is AIML.This thesis focuses on the implementation of an AIML interpreter written in Javascript to allow for a web-based client-side specific usage of AIML chatbots. The interpreter must guarantee the compliance of properly formed AIML documents, perform all the necessary pre-processing duties for the correct usage of the chatbot and ensure the correctness of both pattern matching of user input and chatbot response.The interpreter fully exploits the DOM tree manipulation functions of the jQuery library to achieve said goals, treating AIML files as if they were normal XML files. The result is a well performing, fully functional AIML interpreter tailored around AIML 1.0 specification.

The digitalisation has moved forward since the first website launched in Sweden 1993. Today theinternet is a big source for information that is available 24/7 to the users. All municipalities inSweden have their own websites with information for its citizens about topics like eldercare,schools, and landscape planning to rescue services. 17 out of 290 municipalities had a chatbot atthe beginning of this study. The purpose of this report is to highlight how chatbots within theSwedish municipalities are used and what problems they can face with owning one. This will befrom the perspective of the municipality. The method used is semi structured interviews withrepresentatives from eight municipalities and the developer of a chatbot. From these interviews,and our own study, it was learned that municipalities need to prepare themselves better andunderstand their own requirements while measuring their expectations to those.

Background A chatbot is a type of modern computing program that uses textual or vocal interfaces to replicate human communication or "chitchat.” is widely used in many large-scale applications. The thought behind this technological advancement was to provide users with quick and instantaneous responses to questions that they would ask when conversing through email or by phone, which has been shown to boost productivity among users and lessen the time being spent on tasks. Purpose The main aim of this thesis is to investigate opinions and behaviors, in terms of perceived benefits and drawbacks, of international students on whether or not implementing a chatbot onto a university’s website can be mutually beneficial for both the university to lessen the number of incoming questions and the prospective students in their decision-making process to select their future school. Method To do this, a mockup chatbot was created with Voiceflow software. The Voiceflow software is a cutting-edge creative tool for teams focused on conversational design and product development. It has been aligned with the TAM model described in the research framework. The participants were placed in the role of prospective students searching the JU website for general and specialized information on the university's study programs, financial arrangements, apprenticeships, exchange overseas, and the enrollment procedure. Participants in the mockup are invited to imagine themselves as potential students interested in applying for a higher education degree at Jönköping University in one of five scenarios. Conclusion The findings of this research provide insights into the benefits and the drawbacks of implementing a chatbot within higher educational institutions that are actively recruiting international students with their English-taught programs, exchange programs, courses, traineeships, etc. The main conclusion of this research is that higher educational institutions such as colleges and universities should opt to implement a chatbot within their website in order to facilitate frequently asked questions that otherwise would take time, for example waiting for a representative to answer the phone and/or waiting for an email reply. When students reside in another time zone, students greatly benefit from a chatbot as it is available 24/7, in addition, having all the necessary information for international students under one roof, students are able to quickly navigate through various information that is relevant to them in a few clicks with the use of a chatbot. On the other hand, findings show that although chatbots are indeed very helpful to international students, there are some drawbacks that should be considered. Major drawbacks introduced by this research include the lack of human assistance in cases where the chatbot is unable to answer complex and/or personal questions or cases where students prefer human contact. Additionally, chatbots require round-the-clock maintenance to keep them up to date with displaying the correct information.

This research study aims to investigate the perceptions of millennials towards Chatbot and their purchase intentions in the fashion industry. The study explored how chatbots are perceived by millennials, and how these perceptions influence their purchase intentions. To achieve this, the study used a quantitative approach. The data was collected through an online survey, which was distributed to a sample size of 183 millennials. According to the findings, perceived trust is a strong predictor of purchase intention, on the contrary, perceived enjoyment and perceived ease of use are not. The analysis revealed that customers' perceived trust in Chatbots plays a critical role in favorably affecting their purchase intention. Finally, we suggested that further research explores the potential of chatbots as a marketing tool for fashion brands. This could involve investigating the impact of chatbots on customer engagement, satisfaction, and loyalty, as well as exploring the various design and functionality features that could be implemented to enhance the chatbot experience for consumers.

Chatbots are programs that mimic human conversation using Artificial Intelligence (AI). Recent advances in natural language pro- cessing pave the way for chatbots to generate more human-like responses. Therefore, chatbots are finding more complex tasks to perform, such as emotional support which requires both understanding emotions and the ability to properly respond to them. This work presents a chatbot capable of identifying the user's personality and creating responses based on that. During this process, emotion detection is being used to detect and react to users' emotions. The chatbot uses a dynamic knowledge graph to save information as the conversation goes on. A user study confirmed that these additions were both noticeable and improved the user's sense that the chatbot was getting to know them as a person. Long-term, we hope this research will help create chatbots that provide emotional support for caregivers who work with people with dementia.

Chatbots are the next big improvement in the era of conversational services. A chatbot is a virtual person who can carry out a conversation with a human about a certain subject, using interactive textual skills. Currently, there are many cloud-based chatbots services that are being developed and improved such as IBM Watson, well known for winning the quiz show “Jeopardy!” in 2011. Chatbots are based on a large amount of structured data. They contains many examples of questions that are associated to a specific intent which represents what the user wants to say. Those associations are currently being done by hand, and this project focuses on improving this data structuring using both supervised and unsupervised algorithms. A supervised reclassification using an improved Barycenter method reached 85% in precision and 75% in recall for a data set containing 2005 questions. Questions that did not match any intent were then clustered in an unsupervised way using a K-means algorithm that reached a purity of 0.5 for the optimal K chosen. / Chatbots är nästa stora förbättring i konversationstiden. En chatbot är en virtuell person som kan genomföra en konversation med en människa om ett visst ämne, med hjälp av interaktiva textkunskaper. För närvarande finns det många molnbaserade chatbots-tjänster som utvecklas och förbättras som IBM Watson, känt för att vinna quizshowen "Jeopardy!" 2011. Chatbots baseras på en stor mängd strukturerade data. De innehåller många exempel på frågor som är kopplade till en specifik avsikt som representerar vad användaren vill säga. Dessa föreningar görs för närvarande för hand, och detta projekt fokuserar på att förbättra denna datastrukturering med hjälp av både övervakade och oövervakade algoritmer. En övervakad omklassificering med hjälp av en förbättrad Barycenter-metod uppnådde 85 % i precision och 75 % i recall för en dataset innehållande 2005 frågorna. Frågorna som inte matchade någon avsikt blev sedan grupperade på ett oövervakad sätt med en K-medelalgoritm som nådde en renhet på 0,5 för den optimala K som valts.