With extensive data available in today's organizations, it has become increasingly important to secure valuable insights through data. As a result, the management of data to support decision-making processes is receiving increasing attention in organizations' IT strategies. The healthcare sector is no exception. However, there is an urgent need for tools that help organizations extract valuable insights from the rapidly growing volumes of data, one of the most important steps of which is data mining. So far, the healthcare sector has not found a way to harness its full potential, due to limited methods to extract useful knowledge hidden in large data sets. Knowledge gained from data mining can help healthcare to better serve patients, but there is a limited comprehensive picture of applications regarding data mining processes in healthcare. Against this background, the purpose of this study is to investigate practical dimensions of the data mining process in healthcare and further identify barriers that can inhibit this process. To answer our research question, we used a qualitative case study with semi structured interviews based on the CRISP-DM framework. Our findings indicate barriers that can inhibit the data mining process, which are related to the objectives, data availability and final reports.

Nowadays it is common for companies to sit on and gather a lot of data related to their business. The size of this data is often too large to be analyzed by hand and it is therefore becoming more and more common to automate this analysis e.g. by running machine learning methods on this data. In this project we attempt at analyzing an unstructured dataset consisting of remarks, found by inspectors, on electrical installations. This is done by firstly clustering the dataset with the goal of having each cluster representing a specific type of error found in the field and then extracting ten keywords from each cluster. We investigate whether these keywords can be used for representing the clusters’ contents in a way that could be useful for a future end-user application. The solution developed in this project was evaluated by constructing a form where the respondents were shown example remarks from a random subset of clusters and got to evaluate both how well the extracted keywords matched the examples and to what degree the example remarks from the same cluster represented the same kind of error. We got a total of 22 responses consisting of 8 professional inspectors and 14 laymen. Our results show that the keyword extraction make sense in connection to the example remarks from the form and that the keywords show promise in describing the content of a cluster. Also, for a majority of the clusters a clear consensus can be seen between the respondents on what keywords they considered as relevant. However the average number of keywords that the respondents considered relevant for each remark (1.40) was deemed too low for us to be able to recommend the solution. Additionally the clustering quality follows the same pattern in showing promise but not quite giving satisfactory results in this study. For future work a larger study should be conducted where several combinations of clustering and keyword extraction methods could be evaluated more thoroughly to be able to draw more decisive conclusions. / Nuförtiden är det vanligt att företag samlar in och sitter på en mängd data kopplad till sin verksamhet. Denna datamängd är ofta för stor för att kunna analyseras för hand. Därför har det blivit allt vanligare att automatisera denna analys genom att köra maskininlärningsmetoder på datan. I detta projekt analyseras ett dataset bestående av fritext-poster innehållande anmärkningar på elinstallationer. Detta görs genom att först klustra datan med målet att varje kluster ska representera en viss typ av anmärkning från fältet för att sedan extrahera 10 st nyckelord från varje kluster. Vår undersökning går sedan ut på att undersöka till vilken grad dessa nyckelord kan sägas representera klustrens innehåll på ett sätt som skulle vara användbart för en applikation för slutanvändare. Den lösning som togs fram i projektet utvärderades genom en enkät där de svarande visades exempel på anmärkningar från ett antal slumpvist valda kluster och sedan fick ta ställning till hur väl nyckelorden passade in på exemplen och också till vilken grad exemplen från samma kluster representerade samma typ av anmärkning. Totalt fick vi in svar från 22 personer, nämligen 8 besiktningsingenjörer och 14 st lekmän. Resultaten visar att de extraherade nyckelorden hade en naturlig koppling till de respektive anmärkningarna från enkäten och att de har potential att förklara innehållet i klustren. Hos en majoritet av klustern kunde vi också se en tydlig samstämmighet bland de svarande i vilka specifika nyckelord som ansågs relevanta. Dock var det genomsnittliga antalet nyckelord som ansågs relevanta för ett anmärkningsexempel (1,40) för lågt för att vi ska kunna rekommendera den utvärderade lösningen. På ett liknande sätt visar våra resultat att klustringen av datan var lovande, men att den inte blev helt tillfredsställande. I ett fortsatt arbete borde en större undersökning göras där flera kombinationer av metoder för klustring och extrahering av nyckelord jämförs grundligare så att säkrare slutsatser kan dras.

The purpose of this study is to explore how ads on Instagram can create a positive attitude for the recipient. This was investigated through a quantitative survey where the respondents, girls belonging to generation Z, got to choose between ads, identify what caught their interest and describe their experience of the ads. The results show that ads with human presence are chosen more often than those without human presence, and there is a slight advantage for those ads with visible face compared to those without visible face. The results also show that when the ads have a visible face, the human is the recipient’s main focus, while ads with a human presence without a visible face are considered to emphasize the product more. The ads with human presence are generally considered to be more inspiring while the most common experience of the ads without human presence is that they are informative. This study complements previous literature by arguing that human presence in itself is a powerful stimulus to capture the attention of recipients on Instagram. We conclude that human presence is a contributing factor to creating a positive attitude for the recipient on Instagram and that it is further enhanced if the ad has a visible face. / Syftet med den här undersökningen är att utforska hur annonser på Instagram kan skapa en positiv inställning hos mottagaren. Det har undersökts genom en kvantitativ enkätstudie där respondenter, tjejer tillhörande generation Z, fick välja mellan annonser, identifiera vad som fångade deras intresse och beskriva hur de uppfattade annonserna. Resultatet av detta visar att annonser med mänsklig närvaro väljs oftare än de utan mänsklig närvaro, och det finns en liten fördel för de annonserna med synligt ansikte jämfört med de utan synligt ansikte. Resultatet visar även att när annonserna har synligt ansikte är människan mottagarens fokus, jämfört med annonser med mänsklig närvaro utan synligt ansikte som anses framhäva erbjudandet mer. De med mänsklig närvaro anses generellt vara mer inspirerande medan den vanligaste uppfattningen av annonserna utan mänsklig närvaro är att de är informativa. Studien kompletterar tidigare litteratur genom att argumentera att mänsklig närvaro i sig är ett kraftfullt stimuli för att fånga mottagarnas uppmärksamhet på Instagram. Vi drar slutsatsen att mänsklig närvaro är en bidragande faktor till att skapa en positiv inställning hos mottagaren på Instagram och att den ytterligare förstärks om annonsen innehåller ett synligt ansikte.

Currently, most long-term human motion classification and prediction tasks are driven by spatio-temporal data of the human trunk. In addition, data with multiple modalities can change idiosyncratically with human motion, such as electromyography (EMG) of specific muscles and respiratory rhythm. On the other hand, progress in Artificial Intelligence research on the collaborative understanding of image, video, audio, and semantics mainly relies on MultiModal Machine Learning (MMML). This work explores human motion classification strategies with multi-modality information using MMML. The research is conducted using the Unige-Maastricht Dance dataset. Attention-based Deep Learning architectures are proposed for modal fusion on three levels: 1) feature fusion by Component Attention Network (CANet); 2) model fusion by fusing Graph Convolution Network (GCN) with CANet innovatively; 3) and late fusion by a simple voting. These all successfully exceed the benchmark of single motion modality. Moreover, the effect of each modality in each fusion method is analyzed by comprehensive comparison experiments. Finally, statistical analysis and visualization of the attention scores are performed to assist the distillation of the most informative temporal/component cues characterizing two qualities of motion. / För närvarande drivs uppgifter som långsiktig klassificering och förutsägelse av mänskliga rörelser av spatiotemporala data från människans bål. Dessutom kan data från flera olika modaliteter förändras idiosynkratiskt med mänsklig rörelse, t.ex. elektromyografi (EMG) av specifika muskler och andningsrytm. Å andra sidan bygger forskning inom artificiell intelligens för samtidig förståelse av bild, video, ljud och semantik huvudsakligen på multimodal maskininlärning (MMML). I det här arbetet undersöks strategier för klassificering av mänskliga rörelser med multimodal information med hjälp av MMML. Forskningen utförs med hjälp av Unige-Maastricht Dance dataset. Uppmärksamhetsbaserade djupinlärningsarkitekturer föreslås för modal fusion på tre nivåer: 1) funktionsfusion genom Component Attention Network (CANet), 2) modellfusion genom en innovativ fusion av Graph Convolution Network (GCN) med CANet, 3) och sen fusion genom en enkel omröstning. Alla dessa överträffar riktmärket med en enda rörelsemodalitet. Dessutom analyseras effekten av varje modalitet i varje fusionsmetod genom omfattande jämförelseexperiment. Slutligen genomförs en statistisk analys och visualiseras av uppmärksamhetsvärdena för att hjälpa till att hitta de mest informativa temporala signaler eller komponentsignaler som kännetecknar två typer av rörelse.

På grund av digitaliseringen är kunskapsarbetare inte längre bundna till sina arbetsplatser för att utföra sitt arbete. Tillgången till informations- och kommunikationsverktyg innebär att allt fler arbetslag har medarbetare som arbetar på distans, vilket innebär nya utmaningar och möjligheter för chefer sett både till kommunikation och koordination. Coronapandemin med dess restriktioner har inneburit en större andel distansarbetare och flexibla team, vilket skapar ett ökat behov av kunskap inom området. Krav på ledarskap förändrades i och med ICT verktygens växande roll på arbetsplatser, vilket är bakgrunden till denna studie. Därför ämnar denna uppsats skapa en fördjupad förståelse för hur chefer leder och koordinerar sina anställda med hjälp av ICT verktyg på den flexibla arbetsplatsen. Utifrån ett tvärvetenskapligt angreppssätt där Företagsekonomi och Människa-dator interaktion förenas, har chefer intervjuats på två fallorganisationer som har liknande systemstruktur för internkommunikation. Med en dualistisk syn på tekniska och sociala aspekter, kan uppsatsen bidra till en ökad förståelse för e-ledarens roll ur både ett tekniskt och ett socialt perspektiv. Våra resultat i kombination med tidigare studier, antyder att chefer inom kunskapsintensiva arbetsplatser möter vissa utmaningar med koordination och kommunikation med hjälp av ICT verktyg, både när det kommer till tekniska och sociala aspekter. Den uppgiftsorienterade kommunikationen och koordinationen främjas av ICT verktyg i större utsträckning, än vad gäller den sociala interaktionen och kommunikationen.

This pilot study was conducted to test if there are differences in occurrence of red-listed xylophagous fungi in forests dependent on degrees of human impact on the forests. Three main degrees of human impact was investigated: little impact (natural forest); medium impact (semi-natural forest) and high impact (monoculture plantation). These forests were compared in three geographically distinct areas within the same municipality, Vindeln. Within each forest type, three experimental plots were randomly selected, resulting in a total of 27 research plots. The study was conducted in northern Sweden, Västerbotten county in the following locations: Svartberget, Skatan and Kulbäcksliden. The pilot study found significant differences between natural forests and monoculture plantations. The natural forests harboured the most red-listed species, followed by the semi-natural forests, while the monoculture plantations had the fewest. The semi-natural was closer to the natural forest but did not yield significant differences when comparing the various areas. Despite the small dataset, the results are clear that the natural forests harbour the highest abundance of red-listed xylophagous fungi when comparing the degree of human impact in three different forest ecosystems.

This study explores operationalizing UX practices in agile software development teams to integrate accessibility in B2B software products. We conducted a qualitative case study, collecting data through a user-centered approach with interviews, a workshop, prototyping, and user testing. Our findings highlight that the sporadic involvement of UX professionals, the B2B context’s restriction of communication with end-users, and the perception of accessibility as a non-critical concern, all limit the operationalization of UX practices. Additionally, the importance of implementing structured approaches to integrate UX practices. This study contributes theoretically by broadening the literature on integrating accessibility through UX practices within agile processes, providing insights into the challenges and strategies of B2B environments, and practically by introducing a prototype ecosystem to help product teams embed UX practices into their workflow for enhancing accessibility.

This research addresses the growing applications and impacts of AI-generated digital human avatars from software suites like HeyGen. By exploring the role of trust in mediating user interaction with such technology, this study establishes a basic hierarchical model which supports some foundational theories of human-computer interaction, while also calling into question some more recent theories and models previously used to evaluate avatar technology. By modeling user behavior and user preference through the lens of trust, this study is able to demonstrate how this emerging technology is similar to its predecessors and their relevant theories, while also establishing this technology as something distinctly new and largely untested. This research serves as an exploratory study, using notions of social presence, anthropomorphic design, social trust, technological trust, and human source-bias to separate this generation of AI Avatar technology from its predecessors, and determine what theories and models govern the use of this new technology. The findings from this study and their impacts on use-cases are then applied, speculating on prosocial as well as potentially unethical uses of such technology. Finally, this study problematizes the loss of “primary trust” that this technology may afford, highlighting the importance not only of continued research, but also rapid oversight in the deployment of this emerging technology.

Abstract: This thesis investigates the capacity of individuals to detect AI-generated text, and the indicators that enable them to do so. This inquiry is situated in the broader theoretical context of digital capital, the digitization of society, deep mediatization, and AI literacy. Using a quantitative correlation approach, the study tested participants’ accuracy in detecting AI content, and shared factors between participants with high scores on this task. Participants were assessed on a number of self-reported demographic, digital capital, and digital society-based benchmarks in conjunction with AI detection accuracy. The study employed a mix of statistical methods, including logistic regression and point-biserial correlation matrices. However, only a few specific questions within the digital capital and digital society framework had a statistically significant impact on a participant being in the high-accuracy group, and these correlations were weak. Furthermore, two aspects of digital capital actually had a negative effect on the odds of scoring high on the text detection task.  The findings reveal that there is room for more research into what indicators influence human AI detection capabilities, and whether these skills are learnable or inherent to certain individuals. Moreover, the research highlights the necessity of fostering AI literacy, particularly if these capabilities improve human AI detection. While AI systems can ‘catch’ AI-generated text, their efficacy is mixed, and producers of AI text and evaluators are constantly locked in a game of cat-and-mouse, using evolving AI to recognize evolving AI. Thus, human skills are pivotal, lest we become even more dependent on technology in our deeply mediatized society.

This thesis project, conducted in collaboration with Scandinavian Airlines (SAS), investigates how safety-critical internal systems can be designed to enhance usability and user experience through an examination of the Aerodrome Approval system at SAS. Employing a research-through-design approach and utilizing heuristic evaluations, semi-structured interviews, contextual inquiries, and a redesign process, several guidelines for improving usability and user experience have been identified. Key insights reveal that optimizing login functionalities can enhance security and role-specific access, thereby reducing errors and improving the user experience. Consistency in design elements and adherence to standards play a critical role in usability, aiding in error prevention and improving system navigation efficiency. Additionally, effective strategies for error prevention, such as contextual warnings tailored to specific conflicts, help maintain workflow efficiency and prevent user fatigue, whereas ensuring a balanced and timely presentation of information is essential to prevent information overload while still ensuring access to critical data. The project illustrates how multiple usability principles are interconnected yet sometimes conflicting and emphasizes the need to further investigate safety-critical internal systems to a broader extent to be able to identify more generalizable design guidelines in the future.