Department of Information Science and Media Studies
Recent Submissions
-
A survey on popularity bias in recommender systems
(Journal article; Peer reviewed, 2024)Recommender systems help people find relevant content in a personalized way. One main promise of such systems is that they are able to increase the visibility of items in the long tail, i.e., the lesser-known items in a ... -
Malicious Agents and the Power of the Few : On the Logic of Abnormality in Social Networks
(Doctoral thesis, 2024-09-27)Denne avhandlingen befinner seg i skjæringspunktet mellom formallogikk, samfunnsvitenskap, informasjonsvitenskap og forskning innenfor kunstig intelligens. Den er viet til studiet av agenter i multiagent-systemer som ... -
The Information Disorder Level (IDL) Index: A Human-Based Metric to Assess the Factuality of Machine-Generated Content
(Journal article; Peer reviewed, 2023)Large language models have enabled the rapid production of misleading or fake narratives, presenting a challenge for direct detection methods. Considering that generative artificial intelligence tools are likely to be used ... -
Prototyping first-person viewer positions for VR narratives with storyboards and pilot productions
(Journal article; Peer reviewed, 2023)In this article, we present two related approaches to scripting or prototyping VR narratives. We tested storyboarding and pilot production techniques with 40 students over two years, and they were tasked with creating ... -
Beyond the Game: The Role of Mega-Sport Events and Media in Shaping Gender Equality and Women's Empowerment. An Analytical Study of the International Olympic Committee's Influence on Media Representation and Social Change
(Doctoral thesis, 2024-08-30)Denne doktorgradsavhandlingen er en omfattende undersøkelse av forholdet mellom store idrettsarrangementer, mediedekning og implikasjonene for likestilling og kvinners myndiggjøring, med fokus på Den internasjonale olympiske ... -
Constructing hermeneutical relations: a postphenomenological inquiry into immersive VR memory palaces
(Journal article; Peer reviewed, 2023)While VR adaptations of the mnemonic Method of Loci (or the ‘Memory Palace’ technique) show promising results in increasing mnemonic capabilities, little to no research has explored the use and integration of Virtual Memory ... -
Hybrid recommendation by incorporating the sentiment of product reviews
(Journal article; Peer reviewed, 2023)Hybrid recommender systems utilize advanced algorithms capable of learning heterogeneous sources of data and generating personalized recommendations for users. The data can range from user preferences (e.g., ratings or ... -
Deepfake Detection: Analyzing Model Generalization Across Architectures, Datasets, and Pre-Training Paradigms
(Journal article; Peer reviewed, 2023)As deepfake technology gains traction, the need for reliable detection systems is crucial. Recent research has introduced various deep learning-based detection systems, yet they exhibit limitations in generalising effectively ... -
Topical Preference Trumps Other Features in News Recommendation: A Conjoint Analysis on a Representative Sample from Norway
(Journal article; Peer reviewed, 2023)A variety of news articles features can be used to tailor news content. However, only a few studies have actually compared the relative importance of different features in predicting news reading behavior in the context ... -
Understanding How News Recommender Systems Influence Selective Exposure
(Chapter, 2023)News recommender systems (NRSs) offer benefits in the realm of information consumption and person- alized news delivery. Yet, some critics argue that overly personalized news recommendations can pose a threat to democracy ... -
The Interplay between Food Knowledge, Nudges, and Preference Elicitation Methods Determines the Evaluation of a Recipe Recommender System
(Chapter, 2023)Domain knowledge can affect how a user evaluates different aspects of a recommender system. Recipe recommendations might be difficult to understand, as some health aspects are implicit. The appropri- ateness of a recommender’s ... -
Designing for Control in Nurse-AI Collaboration During Emergency Medical Calls
(Chapter, 2023)AI-powered symptom checkers are automating the work of telephone triage nurses in assessing patient urgency. Yet, these systems exclude several vulnerable patient groups and overlook telenurses’ competent interaction with ... -
Self supervised learning and the poverty of the stimulus
(Journal article; Peer reviewed, 2023)Diathesis alternations are the possible expressions of the arguments of verbs in different, systematically related subcategorization frames. Semantically similar verbs such as spill and spray can behave differently with ... -
Automated Claim Detection for Fact-checking: A Case Study using Norwegian Pre-trained Language Models
(Chapter, 2023)We investigate to what extent pre-trained language models can be used for automated claim detection for fact-checking in a low resource setting. We explore this idea by fine-tuning four Norwegian pre-trained language models ... -
JSEEGraph: Joint Structured Event Extraction as Graph Parsing
(Chapter, 2023)We propose a graph-based event extraction framework JSEEGraph that approaches the task of event extraction as general graph parsing in the tradition of Meaning Representation Parsing. It explicitly encodes entities and ... -
Satisfiability of Arbitrary Public Announcement Logic with Common Knowledge is Σ^1_1-hard
(Chapter, 2023)Arbitrary Public Announcement Logic with Common Knowledge (APALC) is an extension of Public Announcement Logic with common knowledge modality and quantifiers over announcements. We show that the satisfiability problem of ... -
Exploring Streamer Audience Interactions on Twitch
(Master thesis, 2024-06-03)This thesis explores the unique interaction between content creators and their audience on Twitch.tv, a social media platform that focuses on live streaming content. The study uses the interaction analysis research method ... -
"Fra bærekraft til trend" - en kvalitativ undersøkelse om hvordan Mari Hetland AS tolker og praktiserer bærekraft gjennom design, produksjon, kommunikasjon og markedsføring i sosiale medier
(Master thesis, 2024-06-03)Denne studien har forsket på hvordan den lokale motebedriften Mari Hetland AS tolker og kommuniserer bærekraft gjennom sine produkter, og gjennom et samarbeid hun har med Embla Bunad. Bedriften Mari Hetland AS driver med ... -
Neural Networks as Argument Generators: Exploring Counter-Argument Generation
(Master thesis, 2024-06-03) -
Hybrid intelligence in video game character ideation
(Master thesis, 2024-06-03)Hybrid Intelligence (HI) increases human-AI collaboration and co-creation, leading to more productive interactions and outcomes. This study, using mainly a research-through-design model, examines the possibilities of hybrid ...