Story-focused news articles are a different type of news articles, containing more visual and interactive elements, developed in order to engage a younger audience for online newspapers. User engagement has been defined as the “emotional, cognitive and behavioral connection between a user and a resource”, and different metrics are used to track the user engagement of the readers on these articles. However, there is no prior research on which of these metrics describe user engagement in the most accurate way. This study therefore aims to find out what metrics to use when measuring user engagement on story-focused articles through interviewing readers of three different story-focused articles and compare their engagement levels with actual metric values tracked. The results show that two out of the three articles can be considered engaging according to the definition, and the metrics they both have in common is high values of scroll depth, low values of bounce rate and high values of page views. The study therefore concludes that a combination of these three metrics describes user engagement in the most accurate way possible. Furthermore, both the engaging articles have a large number of images, galleries and videos compared to the non-engaging article, which indicates that visual elements in different forms are a winning concept for story-focused articles. / Nyhetsartiklar som fokuserar på berättande är en ny typ av nyhetsartiklar som innehåller fler visuella och interaktiva element, utvecklade för att engagera en yngre publik för digitala nyhetssidor. Användarengagemang har tidigare definierats som det “emotionella, kognitiva och beteendemässiga kontakten mellan användaren och resursen”, och olika mätetal används för att mäta användarengagemanget hos läsarna av nyhetsartiklar som fokuserar på berättande. Däremot finns det ingen tidigare forskning på vilka av dessa mätetal som beskriver användarengagemang på bäst sätt. Den här studien har därför som mål att ta reda på vilka mätetal som borde användas vid mätning av användarengagemang för nyhetsartiklar som fokuserar på berättande, genom att intervjua läsare av tre olika artiklar och jämföra deras engagemangsnivå med uppmätta mätetal. Resultaten visar att 2 av de 3 artiklarna kan anses engagerande enligt definitionen, och mätetalen som de båda har gemensamt är ett högt genomsnittligt scrolldjup, låg nivå av studsar och höga siffror för sidvisningar. Studien drar därför slutsatsen att en kombination av dessa tre mätetal beskriver användarengagemang på bästa möjliga sätt. Dessutom har båda de engagerande artiklarna ett stort antal bilder, gallerier och videor jämfört med den icke engagerande artikeln, vilket indikerar att visuella element av olika slag är ett vinnande koncept för historieberättande artiklar.

Background: In the last few years, there has been rapid growth in the use of cryptocurrency, as it is a form of digital currency and was developed using blockchain technology, so it is almost impossible to counterfeit cryptocurrency. Due to these features, it has attracted a lot of popularity and attention in the market. There has been a research gap in predicting accurate cryptocurrency prices by using sentiment analysis. This study will use Artificial Intelligence-based methods and sentiment analysis to develop a model for predicting cryptocurrency prices. By using the mentioned methods in this thesis, the developed model will provide precise results. Objectives: The objective of the thesis is to compare artificial intelligence models for cryptocurrency price prediction and analyze the importance of sentiment analysis by understanding the public pulse in cryptocurrencies and how it affects price fluctuations, analyzing the correlation within news articles, social media posts, and price fluctuations, as well as evaluating the model performance by employing metrics like RSME, MSE, MAE, and R2 error. Methods: The thesis follows the use of a systematic literature review along with an experimental model for comparing artificial intelligence models. Sentiment analysis played a crucial role in understanding market dynamics. By using linear regression, random forest, and gradient boosting algorithms artificial intelligence models are built to predict cryptocurrency prices using sentiment analysis. The developed models are then compared using performance metrics. This research has analyzed and evaluated each model's performance in predicting cryptocurrency prices. Results: The results of the systematic literature review indicated that market sentiment affects cryptocurrency prices. Prices have increased when market sentiment has been positive, whereas prices dropped when sentiment has been negative. The correlation between cryptocurrency values and market mood, however, is complicated as it depends on a variety of factors. Based on the evaluation measures, the random forest artificial intelligence model is the most accurate in predicting cryptocurrency prices after evaluating the three artificial intelligence models. Conclusions: This study utilized sentiment analysis and artificial intelligence to forecast cryptocurrency prices. It highlighted the significance of sentiment analysis as a tool for predicting the short-term price of cryptocurrencies by demonstrating how negative sentiment is correlated with decreases in price compared to positive sentiment with price increases. However, it recognized that it was necessary to take into consideration the complexity and broad range of effects on cryptocurrency markets. Research in the future will examine comprehensive sentiment analysis methods and broadening data sources.

Medias roll i samhället är stor och den spelar en viktig roll i hur samhället ska kunna få ny information om vad som sker runt om i världen. Kvällstidningar rapporterar dagligen om politiska, kulturella och även brottsliga händelser som sker och nyheterna når tusentals människor som får ta del av det. Detta gör att media har ett stort ansvar på sina axlar med att utge opartiska, neutrala och informativa artiklar om det som ämnas att läsas. I denna studie undersöktes hur media framställer olika offer, baserat på den utsattes livssituation, plats för brottet samt vilket sorts brott de utsatts för. Studien genomfördes med hjälp av en tematisk analys, där tre kända fall i Sverige valdes ut för att sedan jämföra och analysera hur media framställer de brottsutsatta. Resultaten påvisar att media har en tendens att framställa brottsutsatta på olika sätt baserat på bland annat deras livssituation och deras bakgrund. Vidare visade det även att medias rapportering av brottsoffer kan vara mer omfattande beroende på hur väl en brottshändelse kan få andra människor att identifiera sig med den brottsutsatta och deras familj. / Media plays a big role in society and is partially responsible for how people in the society receives information about what is happening around the world. Newspapers are daily reporting about political, cultural and even criminal, events that occur, and the news is reached by thousands of people to read. This means that media has a lot of responsibility on their shoulders by giving out impartial, neutral and informative articles for people to read. In this study, we sought to investigate how media presents different types of victims, based on their life situation, the scene of the crime and also what type of crime they were victims of. The study was performed with a thematic analysis, where three known cases in Sweden was chosen, these were then compared and analysed in how they were presented in the media. The results of the study show that media have a tendency to present victims of crime different, depending on their life situation and their background. Furthermore, it showed that media's coverage on victims of crime can be more extensive, depending on how well a crime can make other people identify with the victim and its family.

Extractive text summarization has over the years been an important research area in Natural Language Processing. Numerous methods have been proposed for extracting information from text documents. Recent works have shown great success for English summarization tasks by fine-tuning the language model BERT using large summarization datasets. However, less research has been made for low-resource languages. This work contributes by investigating how BERT can be used for Norwegian text summarization. Two models are developed by applying a modified BERT architecture, called BERTSum, on pre-trained Norwegian and Multilingual BERT. The results are models able to predict key sentences from articles to generate bullet-point summaries. These models are evaluated with the automatic metric ROUGE and in this evaluation, the Multilingual BERT model outperforms the Norwegian model. The multilingual model is further evaluated in a human evaluation by journalists, revealing that the generated summaries are not entirely satisfactory in some aspects. With some improvements, the model shows to be a valuable tool for journalists to edit and rewrite generated summaries, saving time and workload. / <p>Examensarbetet är utfört vid Institutionen för teknik och naturvetenskap (ITN) vid Tekniska fakulteten, Linköpings universitet</p>

Digitalization has made it possible to consume news through both newspapers and social media, but we rarely consider if both platforms share the same news selection. This bachelor study aims to compare which agenda Dagens Nyheter conveys through the choices in the displayed news on the front page of the newspaper and the Instagram feed. The theoretical framework is based on gatekeeping theory, agenda-setting theory and news value theory. Using the quantitative content analysis 486 news articles were coded and analyzed whereof 182 were articles from the news front page and 304 were from the Instagram feed. The results show that hard and soft news are equally represented in the two news outlets. On the other hand, the results also indicate that there are differences regarding the centralization of certain topics, the nature of the news and the main actors. From these results, we conclude that different agendas are conveyed through the news reported between the two mediums.

This work focuses on the summarization task for a set of articles on the same topic. It discusses several possible ways of summarizations and ways to assess their final quality. The implementation of the described algorithms and their application to selected texts constitutes a part of this work. The input texts come from several Czech news servers and they are represented as deep syntactic trees (the so called tectogrammatical layer).

Denna studie inriktar sig på att undersöka hur våldtäktsmyter används i svenska nyhetsartiklar. Mer specifikt undersöks sex stycken nyhetsartiklar varav tre kommer från morgontidningen Dagens Nyheter, respektive tre från kvällstidningen Expressen. Med en kritisk diskursanalys som både teori och metod möjliggör det att analyserar språket på djupet, och hitta underliggande strukturer, som våldtäktsmyter faktiskt är. Det teoretiska ramverket för studien utgår från teorin om kritisk diskursanalys, våldtäktsmyter, offerskapande och medielogik.   För att kunna finna underliggande strukturer och våldtäktsmyter användes olika analysverktyg hämtade från kritisk diskursanalys. Resultatet av denna studie visar att nyhetsartiklarnas manifesta budskap är öppna och feministiska. Underliggande och vid en mer djupgående läsning kan våldtäktsmyter avläsas i den fundamentala grunden. / This study targets how rape myths are used in Swedish news articles. Specifically, it examines three news articles from the morning paper “Dagens Nyheter” as well as three news articles from the evening paper “Expressen”. With a critical discourse analysis we found opportunity for theoretical and methodical analyses of news articles´ linguistics along with underlying structures of such rape myths. The theoretical framework for this study is based on the theory of critical discourse analysis, rape myths, victimization and media logic.   To find underlying structures and rape myths we used several analysis methods from critical discourse analysis. The result of this study shows that the news articles’ manifest messages as open and based on feminism values. However, through deeper interpretation, it is evident that rape myths are continuously used as the fundamental directive.

Με την πραγματικότητα των υπέρογκων και ολοένα αυξανόμενων πηγών κειμένου στο διαδίκτυο, καθίστανται αναγκαία η ύπαρξη μηχανισμών οι οποίοι βοηθούν τους χρήστες ώστε να λάβουν γρήγορες απαντήσεις στα ερωτήματά τους. Η δημιουργία περιεχομένου, προσωποποιημένου στις ανάγκες των χρηστών, κρίνεται απαραίτητη σύμφωνα με τις επιταγές της συνδυαστικής έκρηξης της πληροφορίας που είναι ορατή σε κάθε ``γωνία'' του διαδικτύου. Ζητούνται άμεσες και αποτελεσματικές λύσεις ώστε να ``τιθασευτεί'' αυτό το χάος πληροφορίας που υπάρχει στον παγκόσμιο ιστό, λύσεις που είναι εφικτές μόνο μέσα από ανάλυση των προβλημάτων και εφαρμογή σύγχρονων μαθηματικών και υπολογιστικών μεθόδων για την αντιμετώπισή τους. Η παρούσα διδακτορική διατριβή αποσκοπεί στο σχεδιασμό, στην ανάπτυξη και τελικά στην αξιολόγηση μηχανισμών και καινοτόμων αλγορίθμων από τις περιοχές της ανάκτησης πληροφορίας, της επεξεργασίας φυσικής γλώσσας καθώς και της μηχανικής εκμάθησης, οι οποίοι θα παρέχουν ένα υψηλό επίπεδο φιλτραρίσματος της πληροφορίας του διαδικτύου στον τελικό χρήστη. Πιο συγκεκριμένα, στα διάφορα στάδια επεξεργασίας της πληροφορίας αναπτύσσονται τεχνικές και μηχανισμοί που συλλέγουν, δεικτοδοτούν, φιλτράρουν και επιστρέφουν κατάλληλα στους χρήστες κειμενικό περιεχόμενο που πηγάζει από τον παγκόσμιο ιστό. Τεχνικές και μηχανισμοί που σκοπό έχουν την παροχή υπηρεσιών πληροφόρησης πέρα από τα καθιερωμένα πρότυπα της υφιστάμενης κατάστασης του διαδικτύου. Πυρήνας της διδακτορικής διατριβής είναι η ανάπτυξη ενός μηχανισμού συσταδοποίησης (clustering) τόσο κειμένων, όσο και των χρηστών του διαδικτύου. Στο πλαίσιο αυτό μελετήθηκαν κλασικοί αλγόριθμοι συσταδοποίησης οι οποίοι και αξιολογήθηκαν για την περίπτωση των άρθρων νέων προκειμένου να εκτιμηθεί αν και πόσο αποτελεσματικός είναι ο εκάστοτε αλγόριθμος. Σε δεύτερη φάση υλοποιήθηκε αλγόριθμος συσταδοποίησης άρθρων νέων που αξιοποιεί μια εξωτερική βάση γνώσης, το WordNet, και είναι προσαρμοσμένος στις απαιτήσεις των άρθρων νέων που πηγάζουν από το διαδίκτυο. Ένας ακόμη βασικός στόχος της παρούσας εργασίας είναι η μοντελοποίηση των κινήσεων που ακολουθούν κοινοί χρήστες καθώς και η αυτοματοποιημένη αξιολόγηση των συμπεριφορών, με ορατό θετικό αποτέλεσμα την πρόβλεψη των προτιμήσεων που θα εκφράσουν στο μέλλον οι χρήστες. Η μοντελοποίηση των χρηστών έχει άμεση εφαρμογή στις δυνατότητες προσωποποίησης της πληροφορίας με την πρόβλεψη των προτιμήσεων των χρηστών. Ως εκ' τούτου, υλοποιήθηκε αλγόριθμος προσωποποίησης ο οποίος λαμβάνει υπ' όψιν του πληθώρα παραμέτρων που αποκαλύπτουν έμμεσα τις προτιμήσεις των χρηστών. / With the reality of the ever increasing information sources from the internet, both in sizes and indexed content, it becomes necessary to have methodologies that will assist the users in order to get the information they need, exactly the moment they need it. The delivery of content, personalized to the user needs is deemed as a necessity nowadays due to the combinatoric explosion of information visible to every corner of the world wide web. Solutions effective and swift are desperately needed in order to deal with this information overload. These solutions are achievable only via the analysis of the refereed problems, as well as the application of modern mathematics and computational methodologies. This Ph.d. dissertation aims to the design, development and finally to the evaluation of mechanisms, as well as, novel algorithms from the areas of information retrieval, natural language processing and machine learning. These mechanisms shall provide a high level of filtering capabilities regarding information originating from internet sources and targeted to end users. More precisely, through the various stages of information processing, various techniques are proposed and developed. Techniques that will gather, index, filter and return textual content well suited to the user tastes. These techniques and mechanisms aim to go above and beyond the usual information delivery norms of today, dealing via novel means with several issues that are discussed. The kernel of this Ph.d. dissertation is the development of a clustering mechanism that will operate both on news articles, as well as, users of the web. Within this context several classical clustering algorithms were studied and evaluated for the case of news articles, allowing as to estimate the level of efficiency of each one within this domain of interest. This left as with a clear choice as to which algorithm should be extended for our work. As a second phase, we formulated a clustering algorithm that operates on news articles and user profiles making use of the external knowledge base of WordNet. This algorithm is adapted to the requirements of diversity and quick churn of news articles originating from the web. Another central goal of this Ph.d. dissertation is the modeling of the browsing behavior of system users within the context of our recommendation system, as well as, the automatic evaluation of these behaviors with the obvious desired outcome or predicting the future preferences of users. The user modeling process has direct application upon the personalization capabilities that we can over on information as far as user preferences predictions are concerned. As a result, a personalization algorithm we formulated which takes into consideration a plethora or parameters that indirectly reveal the user preferences.

The ability to automatically analyze and segment news articles by their content is a growing research field. This thesis explores the unsupervised machine learning method topic modeling applied on Swedish news articles for generating topics to describe and segment articles. Specifically, the algorithms non-negative matrix factorization (NMF) and the latent Dirichlet allocation (LDA) are implemented and evaluated. Their usefulness in the news media industry is assessed by its ability to serve as a uniform categorization framework for news articles. This thesis fills a research gap by studying the application of topic modeling on Swedish news articles and contributes by showing that this can yield meaningful results. It is shown that Swedish text data requires extensive data preparation for successful topic models and that nouns exclusively and especially common nouns are the most suitable words to use. Furthermore, the results show that both NMF and LDA are valuable as content analysis tools and categorization frameworks, but they have different characteristics, hence optimal for different use cases. Lastly, the conclusion is that topic models have issues since they can generate unreliable topics that could be misleading for news consumers, but that they nonetheless can be powerful methods for analyzing and segmenting articles efficiently on a grand scale by organizations internally. The thesis project is a collaboration with one of Sweden’s largest media groups and its results have led to a topic modeling implementation for large-scale content analysis to gain insight into readers’ interests.

This thesis has been carried out as there has been a need to expand research in men's violence against women in close relationships. This by a historical comparison to discover causal explanation and conceptions with a focus on change and continuity over time. Men's violence against women needs more research, although new interventions such as laws have been put into place, the problem still remains in society. The thesis will focus on finding change and continuity over time. Analyzing the area through a historical perspective can further contribute to a greater insight into the problem today, to reduce the risk of repetition of the past, regarding conceptions on gender and violence and not make the problem invisible. The material that has been used in the thesis is based on news articles from Dagens Nyheter and Svenska Dagbladet, based on four selected time periods during the 1900–2020s. The analysis focus on the public's perceptions and causal explanations of men's violence against women in close relationships. The result of the analysis concluded, among other things, that research and news articles do not always correspond and that society's perceptions and causal explanations have both altered and continued. A finding  in the thesis is that jealousy and men's feelings are two relatively unexplored areas.