Narratives are fundamental to our understanding of the world, and they are pervasive in all activities that involve representing events in time. Narrative analysis has a series of applications in computational journalism, intelligence analysis, and misinformation modeling. In particular, narratives are a key element of the sensemaking process of analysts. In this work, we propose a narrative model and visualization method to aid analysts with this process. In particular, we propose the narrative maps framework—an event-based representation that uses a directed acyclic graph to represent the narrative structure—and a series of empirically defined design guidelines for map construction obtained from a user study. Furthermore, our narrative extraction pipeline is based on maximizing coherence—modeled as a function of surface text similarity and topical similarity—subject to coverage—modeled through topical clusters—and structural constraints through the use of linear programming optimization. For the purposes of our evaluation, we focus on the news narrative domain and showcase the capabilities of our model through several case studies and user evaluations. Moreover, we augment the narrative maps framework with interactive AI techniques—using semantic interaction and explainable AI—to create an interactive narrative model that is capable of learning from user interactions to customize the narrative model based on the user's needs and providing explanations for each core component of the narrative model. Throughout this process, we propose a general framework for interactive AI that can handle similar models to narrative maps—that is, models that mix continuous low-level representations (e.g., dimensionality reduction) with more abstract high-level discrete structures (e.g., graphs). Finally, we evaluate our proposed framework through an insight-based user study. In particular, we perform a quantitative and qualitative assessment of the behavior of users and explore their cognitive strategies, including how they use the explainable AI and semantic interaction capabilities of our system. Our evaluation shows that our proposed interactive AI framework for narrative maps is capable of aiding users in finding more insights from data when compared to the baseline. / Doctor of Philosophy / Narratives are essential to how we understand the world. They help us make sense of events that happen over time. This research focuses on developing a method to assist people, like journalists and analysts, in understanding complex information. To do this, we introduce a new approach called narrative maps. This model allows us to extract and visualize stories from text data. To improve our model, we use interactive artificial intelligence techniques. These techniques allow our model to learn from user feedback and be customized to fit different needs. We also use these methods to explain how the model works, so users can understand it better. We evaluate our approach by studying how users interact with it when doing a task with news stories. We consider how useful the system is in helping users gain insights. Our results show that our method aids users in finding important insights compared to traditional methods.

Voice assistants are a remarkable example of the potential for AI to become further entwined with social life. However, they are produced by some of the world’s largest tech corporations and are rooted in capitalistic processes that depend on user data. This thesis presents a qualitative exploratory study of voice assistants. Through a combination of interviews and theoretical analysis, it focuses on participants’ perceptions and experiences with these AI agents and how they are embedded in the bigger picture of surveillance capitalism. The findings reveal the physical characteristics and personality traits that participants in this study ascribe to voice assistants, highlighting the implications of treating voice assistants as personified agents and the factors contributing to these perceptions. Further, this thesis examines how surveillance capitalism is present in participant interactions with these technologies and identifies how its reach into people’s lives is provoked by their design and background contexts. Lastly, it provides an overview of corporate power in the tech industry and how the structural, cultural, and political circumstances enable and legitimize big tech’s authority in digital environments and how this situates the individual and their capacity to contend with technological issues. / Graduate / 2023-07-12

Attention-deficit/hyperactivity disorder (ADHD), is a behaviour disorder, usually first diagnosed in childhood, that is characterized by inattention, impulsivity, and hyperactivity. ADHD is often associated with co-morbid disorders like bipolar disorder, anxiety, depression, and substance abuse. The diagnosis of ADHD is clinically established by a review of symptoms and impairment from the child’s young age. There are numerous assistive technologies that exist for people suffering from ADHD but there exists a research gap in developing self-reflective tools for people with neurodevelopmental disorders. This paper bridges this research gap for students at Malmö University. This project will focus on developing a personalized interactive AI-based system that captures contextual data, analyses it to find relevant patterns in user’s behaviour, and visualizes it effectively to provide students with ADHD with insights into the parameters influencing the nature of their disorder. The project is performed under a Double Diamond method which allows for iteration. The methods used mostly comprise co-design methods to ensure the concept caters to the user’s needs. The project is based on learnings from three key areas: Interactive AI, Personal Informatics and Systems as dialogue partners.