Cette étude examine comment les élèves communiquent par écrit lorsqu'ils savent que leur interlocuteur est un autre élève humain par rapport à la façon dont ils communiquent lorsqu'ils savent que leur partenaire est un « chatbot », un agent conversationnel artificiel qui communique par écrit en utilisant le langage naturel. Les participants sont des lycéens d’un cours de français langue étrangère (FLE) en Suède. Les élèves ont écrit à leurs pairs via la messagerie instantanée (IM) et au chatbot via un site Webb. Les conversations ont été comparées, et leurs variables linguistiques ont été distinguées selon les dimensions suivantes : mots par message et par conversation, messages par conversation, diversité lexicale et fréquence d'émoticônes. Au cours des dernières années, tant les linguistes que les chercheurs en Intelligence Artificielle ont été contraints de traiter des problèmes de contexte, de syntaxe, de sémantique et de pragmatique (Rosenberg, 1975). Il existe des études qui abordent la question de la coopération entre la linguistique et le traitement automatique du langage naturel (TALN) qui se concentrent sur la façon dont les chatbots communiquent par écrit avec les humains. Cependant, cette étude est concentrée sur l'humain, évaluant la langue et distinguant les caractéristiques linguistiques utilisées du côté de l’humain conversant avec un chatbot. Les résultats ont montré que les messages élèves-chatbot contenaient moins de mots par message que ceux envoyés à un autre élève, mais les élèves ont envoyé plus de deux fois plus de messages au chatbot qu'à leurs pairs. L'étude a révélé qu'il existe un niveau de motivation plus élevé chez les élèves lorsqu'ils s'engagent dans des conversations avec l'agent artificiel par rapport aux autres étudiants.

Chatbots are becoming increasingly popular in various industries, and thereare many options available for businesses and organisations. Several studieshave investigated open-source chatbots and identified their core strengths,implementation, and integration capabilities however few have investigatedopen-source chatbot frameworks and libraries in a specific use case such asmedicine. The project's objective was to evaluate a selection of chatbots ormore specifically two frameworks: Botkit and Rasa, and two libraries:ChatterBot, and Natural which was utilised together with Botkit and alanguage model which is DialoGPT. The evaluation focuses specifically onaccuracy, consistency, and response time. Frequently asked questions fromthe World Health Organization and COVID-19 related Dialogue Datasetfrom GitHub were utilised to test the chatbots' abilities in handling differentqueries and accuracy was measured through metrics like Jaccard similarity,bilingual evaluation understudy (BLEU), and recall oriented gistingevaluation (ROUGE) scores, consistency through Jaccard similarity betweenthe generated responses and response time was taken to be the average timefor a response in seconds. The analysis revealed unique strengths andlimitations for each chatbot model. Rasa displayed robust performance inaccuracy, consistency, and customisation capabilities if the chatbot works ina particular topic with acceptable response times. DialoGPT demonstratedstrong conversational abilities and contextually relevant responses withtrade-offs in consistency. ChatterBot showed consistency, though sometimesstruggled with advanced queries, and Botkit with Natural stood out for itsquick response times, albeit with limitations in accuracy and scalability.Despite implementation challenges, these open-source frameworks, libraries,and models offer promising solutions for organisations intending to harnessconversational agents' technology. The study suggests encouraging furtherexploration and refinement in this rapidly evolving field.

Northvolt is a Swedish battery manufacturing company that specializes in the production of sustainable lithium-ion batteries for electric vehicles and energy storage systems. Established in 2016, the company has experienced significant growth in recent years. This growth has presented a major challenge for the IT Support team, as they face a substantial volume of ITrelated inquiries. To address this challenge and allow the IT Support team to concentrate on more complex support tasks, a question-answering chatbot has been implemented as part of this thesis project. The chatbot has been developed using the Microsoft Bot Framework and leverages Microsoft cloud services, specifically Azure Cognitive Services, to provide intelligent and cognitive capabilities for answering employee questions directly within Microsoft Teams. The chatbot has undergone testing by a diverse group of employees from various teams within the organization and was evaluated based on three key metrics: effectiveness (including accuracy, precision, and intent recognition rate), efficiency (including response time and scalability), and satisfaction. The test results indicate that the accuracy, precision, and intent recognition rate fall below the required thresholds for production readiness. However, these metrics can be improved by expanding the knowledge base of the bot. The chatbot demonstrates impressive efficiency in terms of response time and scalability, and its user-friendly nature contributes to a positive user experience. Users express high levels of satisfaction with their interactions with the bot, and the majority would recommend it to their colleagues, recognizing it as a valuable service solution that will benefit all employees at Northvolt in the future. Moving forward, the primary focus should be on expanding the knowledge base and effectively communicating the bot’s purpose and scope to enhance effectiveness and satisfaction. Additionally, integrating the bot with advanced AI features, such as OpenAI’s language models available within Microsoft’s ecosystem, would elevate the bot to the next level.

This paper researches how different amounts of data affect different word vector models for classification of dialog system user input. A hypothesis is tested that there is a data threshold for dense vector models to reach the state-of-the-art performance that have been shown with recent research, and that character-level n-gram word-vector classifiers are especially suited for Swedish classifiers–because of compounding and the character-level n-gram model ability to vectorize out-of-vocabulary words. Also, a second hypothesis is put forward that models trained with single statements are more suitable for chat user input classification than models trained with full conversations. The results are not able to support neither of our hypotheses but show that sparse vector models perform very well on the binary classification tasks used. Further, the results show that 799,544 words of data is insufficient for training dense vector models but that training the models with full conversations is sufficient for single statement classification as the single-statement- trained models do not show any improvement in classifying single statements. / Detta arbete undersöker hur olika datamängder påverkar olika slags ordvektormodeller för klassificering av indata till dialogsystem. Hypotesen att det finns ett tröskelvärde för träningsdatamängden där täta ordvektormodeller när den högsta moderna utvecklingsnivån samt att n-gram-ordvektor-klassificerare med bokstavs-noggrannhet lämpar sig särskilt väl för svenska klassificerare söks bevisas med stöd i att sammansättningar är särskilt produktiva i svenskan och att bokstavs-noggrannhet i modellerna gör att tidigare osedda ord kan klassificeras. Dessutom utvärderas hypotesen att klassificerare som tränas med enkla påståenden är bättre lämpade att klassificera indata i chattkonversationer än klassificerare som tränats med hela chattkonversationer. Resultaten stödjer ingendera hypotes utan visar istället att glesa vektormodeller presterar väldigt väl i de genomförda klassificeringstesterna. Utöver detta visar resultaten att datamängden 799 544 ord inte räcker till för att träna täta ordvektormodeller väl men att konversationer räcker gott och väl för att träna modeller för klassificering av frågor och påståenden i chattkonversationer, detta eftersom de modeller som tränats med användarindata, påstående för påstående, snarare än hela chattkonversationer, inte resulterar i bättre klassificerare för chattpåståenden.

With the rapidly increasing rate of development artificial intelligence (AI) has experienced in recent years, more and more companies have begun to recognize the benefits and possibilities of the technology. This study is a qualitative interview study that has explored and evaluated which challenges are encountered today in customer services and which driving forces and barriers exist in introducing an AI-driven solution with a focus on chatbots. Five semi-structured interviews with people who hold a role as a person responsible for customer service at Monitor ERP System have created the resulting material. According to the respondents, AI and chatbots will have a major impact on customer service, opening many development opportunities. This opens to solve the challenges identified today, which according to the respondents are the new demands from the generational shift, manual- and repetitive work, and finally the lack of time and resources. The driving forces that have been identified for introducing an AI-driven chatbot are stronger corporate branding, increased productivity, higher customer satisfaction, improved work climate, and increased time- and cost efficiency. But getting to the stage where AI and chatbots are used in a business is not entirely without its barriers. The barriers that could be identified are the continued weight of the human factor, difficulties with customer- and employee acceptance, lack of skills, and the complexity and useful data. Even though several difficulties and barriers are expected along the way, the respondents look enthusiastically and expectantly at the development and the future opportunities AI and chatbots can contribute to customer service. / Med den kraftigt ökande utvecklingstakt artificiell intelligens (AI) har upplevt de senaste åren har allt fler företag börjat inse fördelarna och möjligheterna med teknologin. Denna studie är en kvalitativ intervjustudie som har utforskat och utvärderat vilka utmaningar som möts idag inom kundtjänster och vilka drivkrafter samt hinder som finns med att införa en AI-driven lösning med fokus på chattbotar. Fem semistrukturerade intervjuer med personer som besitter en roll som huvudansvarig inom kundtjänsten hos Monitor ERP System har skapat resultatmaterialet. AI och chattbotar kommer enligt respondenterna ha en stor påverkan på kundtjänster och det öppnar upp för många olika utvecklingsmöjligheter. Detta öppnar också upp för att lösa de utmaningar som identifierats idag vilka enligt respondenterna är de nya kraven från generationsskiftet, manuellt- och repetitivt arbete och till sist bristen på tid och resurser. De drivkrafter som identifierats för att införa AI-drivna chattbotar är starkare företagsvarumärke, ökad produktivitet, höjd kundnöjdhet, förbättrat arbetsklimat och ökad tid- och kostnadseffektivitet. Men att komma till det stadie då AI och chattbotar används i verksamheten är inte helt utan hinder. De hinder som identifierats är vikten av mänskliga faktorn, svårigheter med kund- och medarbetaracceptans, kompetensbrist och komplexiteten samt användbarheten av data. Trots att flera svårigheter och hinder förväntas på vägen ser respondenterna entusiastiskt och förväntansfullt på utvecklingen och de framtida möjligheterna AI och chattbotar kan bidra med till kundtjänster.

ВКР (магистерская диссертация) состоит из введения, трех глав, заключения, библиографического списка, включающего 60 наименований. Работа включает 8 таблиц и 26 рисунков. Общий объем ВКР (магистерской диссертации) – 76 страниц. Ключевые слова: оптимизация бизнес-процессов, чат-бот, план проекта, организационная структура, удержание клиентов, повышение лояльности. Актуальность исследования заключается в необходимости использования онлайн-сервисов для взаимодействия между организацией и клиентами в целях сокращения временных издержек текущего бизнес-процесса по консультированию пользователей, а также для повышения лояльности существующих клиентов и привлечения новых с помощью ИТ-решения как конкурентным преимуществом. Цель исследования построение проекта и разработка чат-бота для оптимизации бизнес-процесса консультирования клиентов. В соответствии с темой и целью работы были поставлены следующие задачи: изучить теоретические основы о видах чат-ботов и их применении; составить описание рабочей деятельности технических специалистов на портале «Пульс цен»; построить модель AS-IS бизнес-процесса консультирования клиентов в нотации IDEF0; построить модель TO-BE бизнес-процесса консультирования клиентов в нотации IDEF0; составить план проекта по разработке чат-бота для автоматизации бизнес-процесса консультирования существующих клиентов площадки MS Project; проанализировать возможные риски проекта и предложить решения; провести расчет экономической эффективности проекта; реализовать проект согласно приведенному плану. Объектом исследования выступает технология чат-бота для консультирования клиентов по работе с торговой площадкой «Пульс цен». Предмет исследования: бизнес-процесс консультации клиентов. Научная новизна исследования состоит во внедрении технологии чат-бота в процесс консультирования клиентов торговой площадки «Пульс цен», что будет значимым преимуществом по сравнению с конкурентами. Практическая значимость исследования заключается в применении авторских предложений по оптимизации бизнес-процесса консультирования клиентов. Эффективность рекомендаций – предложенные автором рекомендации по внедрению ИТ-сервиса для предоставления ответов на запросы клиентов торгового портала позволят оптимизировать процесс консультирования клиентов техническими специалистами. Прогнозируется повышение лояльности клиентов, за счет чего будет увеличен процент удержания пользователей в положительном исходе во 2 квартале 2022 г. процент коэффициента удержания клиентов составит около 75%. / The WRC (master's thesis) consists of an introduction, three chapters, a conclusion, a bibliographic list including 60 titles. The work includes 8 tables and 26 figures. The total volume of the WRC (master's thesis) is 76 pages. Keywords: optimization of business processes, chatbot, project plan, organizational structure, customer retention, loyalty increase. The relevance of the research lies in the need to use online services for interaction between the organization and customers in order to reduce the time costs of the current business process for consulting users, as well as to increase the loyalty of existing customers and attract new ones using an IT solution as a competitive advantage. The purpose of the study is to build a project and develop a chatbot to optimize the business process of consulting clients. In accordance with the topic and purpose of the work, the following tasks were set: to study the theoretical foundations of the types of chatbots and their application; create a description of the working activities of technical specialists on the portal "Pulse of Prices"; build an AS-IS model of the business process of consulting clients in IDEF0 notation; build a TO-BE model of the business process of consulting clients in IDEF0 notation; create a project plan for the development of a chatbot for automating the business process of consulting existing clients of the MS Project platform; analyze the possible risks of the project and offer solutions; to calculate the economic efficiency of the project; implement the project according to the given plan. The object of the research is the chatbot technology for advising clients on working with the Pulse of Prices trading platform. Subject of research: the business process of consulting clients. The scientific novelty of the research consists in the introduction of chatbot technology into the process of consulting clients of the Pulse of Prices trading platform, which will be a significant advantage compared to competitors. The practical significance of the research lies in the application of the author's proposals for optimizing the business process of consulting clients. Effectiveness of recommendations-the recommendations proposed by the author on the implementation of an IT service for providing answers to customer requests of the trading portal will optimize the process of consulting clients by technical specialists. It is predicted that customer loyalty will increase, due to which the percentage of user retention in a positive outcome will be increased in the 2nd quarter of 2022.The percentage of customer retention will be about 75%.

Kunskapshantering är ett forskningsområde som handlar om att samla in, dela, förvalta samt applicera kunskap. Chatbotars användningsområde har idag främst varit för att öka den operativa effektiviteten, personifiera organisationers kundtjänst och genomföra datadrivna beslut. Tidigare forskning visar att användning av chatbotar för att förbättra arbetsprocesser som kunskapshantering är ett underforskat område. Därav syftar denna studie till att öka medvetenheten och förståelsen för chatbotars potential inom kunskapsintensiva organisationer. Studien antog en kvalitativ ansats som inleddes med en litteraturstudie som användes för att formulera intervjuguiden. Datainsamlingen har genomförts genom semistrukturerade intervjuer. De teman som identifierades i studien är: Intern och extern dokumentation, informationssökning och problemlösning, samt kommunikation och kunskapsdelning. Studien diskuterar hur chatbotar kan användas som stöd inom dessa teman.  Studien drar slutsatsen att chatbotar kan stödja kunskapsintensiva organisationer genom att agera som en smart assistent. Däremot lyfter studien upp begränsningar och etiska aspekter avseende användningsområdet.   Studiens bidrag till befintlig forskning består av förslag på hur chatbotar kan stödja kunskapshanteringsprocessen genom studiens analytiska teman, vilket är en stark reflektion av kunskapshanteringsprocessen. / Knowledge management is a research area that deals with collecting, sharing, managing, and applying knowledge. The primary use of chatbots today has been to increase operational efficiency, personalize customer service in organizations, and carry out data-driven decisions. Previous research indicates that the use of chatbots to improve work processes such as knowledge management is an under-researched area. Therefore, this study aims to increase awareness and understanding of the potential of chatbots in knowledge-intensive organizations. The study adopted a qualitative approach that began with a literature review, which was used to formulate the interview guide. Data collection was carried out through semi-structured interviews. The themes identified in the study are: Internal and external documentation, information search and problem solving, and communication and knowledge sharing. The study discusses how chatbots can be used to support these themes. The study concludes that chatbots can support knowledge-intensive organizations by acting as a smart assistant. However, the study raises limitations and ethical aspects concerning the area of use. The study's contribution to existing research consists of suggestions on how chatbots can support the knowledge management process through the study's analytical themes, which is a strong reflection of the knowledge management process.

No description available.

Providing context behind customer feedback remains a challenge for company’s who rely on approaching Customer Experience (CX) through standardized Customer Satisfaction (CS) metrics like Net Promoter Score (NPS), Customer Satisfaction Score (CSAT), and Customer Effort Score (CES). Practical guidelines for monitoring CS throughout the customer journey are limited, creating a gap in academic research. This study addresses this gap by offering practical guidelines for CS, actionable insights, and alternative survey design strategies within the context of invoicing. Utilizing a Research-through-Design (RtD) approach guided by the Double Diamond design model, the study consists of four phases: Discover, Define, Develop, and Deliver. From a service design perspective using qualitative methods, the study acquires and analyzes both organizational and customer insights. Synthesized empirical findings emphasize the need for a more comprehensive approach that targets specific phases of the customer journey utilizing a more customer- centric approach, paving the way for alternative methods that reaches beyond just simply measuring CS. Introducing the concept of a personal companion, the study presents a dialogical approach where surveys are experienced as ongoing interactions rather mere tasks. By highlighting the importance of contextualization, alternative survey approaches, and a dialogical approach, this research aims to guide company’s in managing customer feedback strategies.

In recent years, generative AI has made significant strides, likely leaving an irreversible mark on contemporary society. The launch of OpenAI's ChatGPT 3.5 in 2022 manifested the greatness of the innovative technology, highlighting its performance and accessibility. This has led to a demand for implementation solutions across various industries and companies eager to leverage these new opportunities generative AI brings. This thesis explores the common operational challenges faced by a small-scale Tech Enterprise and, with these challenges identified, examines the opportunities that contemporary generative AI solutions may offer. Furthermore, the thesis investigates what type of generative technology is suitable for adoption and how it can be implemented responsibly and sustainably. The authors approach this topic through 14 interviews involving several AI researchers and the employees and executives of a small-scale Tech Enterprise, which served as a case company, combined with a literature review.  The information was processed using multiple inductive thematic analyses to establish a solid foundation for the investigation, which led to the development of a Proof of Concept. The findings and conclusions of the authors emphasize the high relevance of having a clear purpose for the implementation of generative technology. Moreover, the authors predict that a sustainable and responsible implementation can create the conditions necessary for the specified small-scale company to grow.  When the authors investigated potential operational challenges at the case company it was made clear that the most significant issue arose from unstructured and partially absent documentation. The conclusion reached by the authors is that a data management system powered by a Retrieval model in a LLM presents a potential path forward for significant value creation, as this solution enables data retrieval functionality from unstructured project data and also mitigates a major inherent issue with the technology, namely, hallucinations. Furthermore, in terms of implementation circumstances, both empirical and theoretical findings suggest that responsible use of generative technology requires training; hence, the authors have developed an educational framework named "KLART".  Moving forward, the authors describe that sustainable implementation necessitates transparent systems, as this increases understanding, which in turn affects trust and secure use. The findings also indicate that sustainability is strongly linked to the user-friendliness of the AI service, leading the authors to emphasize the importance of HCD while developing and maintaining AI services. Finally, the authors argue for the value of automation, as it allows for continuous data and system updates that potentially can reduce maintenance.  In summary, this thesis aims to contribute to an understanding of how small-scale Tech Enterprises can implement generative AI technology sustainably to enhance their competitive edge through innovation and data-driven decision-making.