Browsing by Supervisor "Liesenfeld, A."
Now showing 1 - 5 of 5
Results Per Page
Sort Options
Item Autonomatronics in Theme Parks.(2023-01-28) Korff, C.Theme parks around the world draw in many guests each year. These guests come to the parks for the great attractions and the immersive atmosphere, created by animatronics. These life-like characters are sometimes referred to as autonomatronics because of their capabilities to seemingly autonomously speak or move. Drawing on Gibson’s classic theory of affordances, this study examines the effects of various affordances in autonomatronics on the user experience of frequent theme park visitors and fans. The study investigates how these products keep guests entertained and affect their experience within the theme parks, and how the novel AI-driven capabilities influence and impact various affordances in how adult theme park visitors and children interact with autonomatronic characters. The study was performed using an online survey consisting of open and multiple choice questions within the theme park fan community in the Netherlands.Item Can language affect food attractiveness?(2023-07-07) Glaubitz, F.K.The language used on food packaging, advertisements or at restaurants to describe food can influence consumers and the nutritious choices they make. When eating out, one is confronted with factors on restaurant menus such as calorie labels, photos of tempting foods and mouth-watering meal descriptions. By changing menu elements such as food descriptions, people may be more inclined to choose healthy dishes over less healthy options. The current study investigated whether the type of language combined with the healthiness of meals on restaurant menus had a significant effect on order intention, for the first time in Dutch. The different language types were categorised into three levels, namely indulgent, healthy and neutral food words. In an online experiment, 143 participants filled in a questionnaire and rated twelve dishes on 7-point Likert scales. Compared to indulgent and neutral food descriptions, health focused language reduced order intention.Item Morphological Knowledge in Multilingual Large Language Models: A Comparative Analysis of mT5 and ByT5(2024) Đăng, Thi Thao AnhMorphology is a crucial factor for multilingual language modeling as it poses direct challenges for tokenization. Here, we seek to understand how tokenization influences the morphological knowledge encoded in multilingual language models. Specifically, we capture the impact of tokenization by probing two pre-trained language models mT5 and ByT5 sharing same model architecture, training objective, and training data -- which only differ in their tokenization strategies: subword tokenization vs. character-level tokenization. Probing the morphological knowledge encoded in these models on 17 languages, our analyses show that multilingual language models learn the morphological systems of some languages better than others, that morphological information is encoded in the middle and late layers, with morphology being present in earlier layers with standard tokenization, yet character-level models eventually yield commensurate morphological knowledge. Finally, we show that languages with more irregularities require a higher proportion in the pre-training data to compensate for the increased complexity.Item Researching Types of Language on Likeliness to Order Healthy or Unhealthy Restaurant Meals: Menus including Indulgent, Health-focused and Neutral Language.(2023-07-07) Jansen, F.A.W.In this study, an experiment of different types of language was conducted on Dutch natives’ intentions to order a meal from a restaurant menu. The different types of language in this study were indulgent language, health-related and neutral language. The experiment measured the effect of using different types of language on a menu description on order intention. The menu included both healthy and unhealthy meals. The aim of the study was to see whether using a certain type of language can lead to a higher order intention of healthy meals. Unhealthy meals are seen as more filling and satisfying compared to healthy meals. Hence, the unhealthy meals could already have a higher level of order intention. However, the possibility of using language to increase that level was tested here. The study focuses on Dutch participants and therefore the descriptions of the meals were written in the Dutch language. The words used in the descriptions had been rated through sensory norms. Since the study had a within-subjects design, all the meals were described in all types of language but were presented in either indulgent, healthy or neutral language.Item The advantages and disadvantages of start-ups investing in AI chatbot technology for customer service communication: based on an (online) experiment and a semi-structured interview.(2023-01-28) Teunissen, M.L.AI technology used in customer service through online chatbots bring significant gains and higher operational and organizational efficiency (Chen et al., 2021; De Andrade & Tumelero, 2022). In order to compete on a large scale, investing in high resource technological innovations is an important expense. This study aims to investigate whether it is beneficial for start-ups to invest in AI chatbots for their customer service communication and whether the quality of the AI ensures start-ups the same beneficial properties as it does for big corporations. This is a mixed method study, based on an (online) experiment with a within-subject design and a semi-structured interview with Obi4one, a company specialized in AI technology including chatbots. The data was acquired using an online questionnaire with 22 participants, examining one’s attitudinal evaluation, customer satisfaction, behavioural intention while analysing the perceived usefulness regarding two conversations. Taking the interview information into account, it was concluded that chatbots do not cause a significant enhancement for start-ups However, start-ups with a rapid enhancing customer base can benefit from investing in AI chatbots, as it could improve operational efficiency. This study contributes to investing strategies of start-ups as it provides a detailed analysis which can be put into practical use when AI investments are considered.