Skip to main content
Login | Suomeksi | På svenska | In English

Browsing by Subject "recommender systems"

Sort by: Order: Results:

  • Aarne, Onni (2022)
    The content we see is increasingly determined by ever more advanced recommender systems, and popular social media platform TikTok represents the forefront of this development (See Chapter 1). There has been much speculation about the workings of these recommender systems, but precious little systematic, controlled study (See Chapter 2). To improve our understanding of these systems, I developed sock puppet bots that consume content on TikTok as a normal user would (See Chapter 3). This allowed me to run controlled experiments to see how the TikTok recommender system would respond to sock puppets exhibiting different behaviors and preferences in a Finnish context, and how this would differ from the results obtained by earlier investigations (See Chapter 4). This research was done as part of a journalistic investigation in collaboration with Long Play. I found that TikTok appears to have adjusted their recommender system to personalize content seen by users to a much lesser degree, likely in response to a previous investigation by the WSJ. However, I came to the conclusion that, while sock puppet audits can be useful, they are not a sufficiently scalable solution to algorithm governance, and other types of audits with more internal access are needed (See Chapter 5).
  • Tulijoki, Juha-Pekka (2024)
    A tag is a freely chosen keyword that a user attaches to an item. Offering a simple, cheap, and natural way to describe content, tagging has become popular in contemporary web applications. The tag genome is a data structure that contains item-tag relevance scores, i.e., continuous scale numbers from 0 to 1 indicating how relevant a tag is for an item. For example, the tag romantic comedy has a relevance score of 0.97 for the movie Love Actually. With sufficient data, a tag genome dataset can be constructed for any domain. To the best of available knowledge, there are tag genome datasets for movies and books. The tag genome for movies is used in a movie recommender and for various purposes in recommender systems research, such as detecting filter bubbles and serendipity. Creating a diverse tag genome dataset requires an effective machine learning solution, as manual assessment of item-tag relevance scores is impractical. The current state-of-the-art solution, called TagDL, uses features extracted from user-generated tags, reviews, and ratings to employ a multilayer perceptron architecture to predict the item-tag relevance scores. This study aims to enhance TagDL by extracting more features from the embeddings of textual content, namely tags, user reviews, and item titles, using Bidirectional Encoder Representations from Transformers (BERT). The results show that features based on BERT embeddings have a potential positive impact on item-tag relevance score prediction. However, the results do not generalize to both tag genome datasets, improving the results only for the movie dataset. This may indicate that the new features have a stronger impact if the amount of available training data is smaller, as with the movie dataset. Moreover, this thesis discusses future work ideas and implementation possibilities.
  • Haapoja, Jesse (2013)
    As the quantity of material available on the Internet grows, problems finding the right information at the right time may follow. Recommender systems have been created to tackle this problem. This study is centered on a collaborative filtering system for news and magazine articles called Scoopinion. Scoopinion collects behavioral information about the reading habits of the users with a browser plug-in. Collaborative filtering can also be called social filtering. Reasons for the use of online social filtering of news and magazine articles and the perceptions about the process of online social filtering are investigated. Analysis was conducted using grounded theory. Research material was interviews that were conducted to ten Scoopinion-users. Interviews were semi-structured. Interviewees were all native Finns. Their ages ranged from 25 to 34. The results of the data-driven analysis were linked to the prior literature on social influence and social comparison. Findings show that online social filtering of news and magazine articles is used to gain access to material that is somehow outside individual’s normal routines of news browsing, to avert possible information overload and for entertainment in situations, where one has nothing else to do. Individuals interact with the recommendation algorithm of the Scoopinion by suggesting magazines as possible sources of recommendations or simply by reading. The reading time that the service tracks was interpreted as showing interest, but it was stated that the algorithm cannot understand whether something is evaluated as important. When a recommendation can be tied to certain individual, the perceived expertise of the recommender on the topic of the recommended article handles affects how the receiver evaluates the recommendation. Lack of clear information about the way the Scoopinion’s algorithm works led to some misunderstandings. The recommendations the service offered were in some cases falsely thought to originate partly from the reading behavior of the user’s personal social network. The most central references: On recommender systems: Schafer, J. B., Frankowski, D., Herlocker, J., & Sen, S. Collaborative filtering recommender systems (2007). On social influence: Deutsch, M., & Gerard, H. B. A study of normative and informational social influences upon individual judgment (1955); Mason, W. A., Conrey, F. R., & Smith, E. R. Situating social influence processes: Dynamic, multidirectional flows of influence within social networks (2007). On social comparison: Festinger, L. A theory of social comparison processes (1954); Suls, J., Martin, R., & Wheeler, L. Three kinds of opinion comparison: The triadic model (2000). On grounded theory: Glaser, B. Basics of Grounded Theory Analysis: Emergence vs. Forcing (1992); Strauss, A., & Corbin, J. Basics of qualitative research. Grounded theory procedures and techniques (1990).