Sökning: "recommender systems"

Visar resultat 1 - 5 av 135 uppsatser innehållade orden recommender systems.

  1. 1. Ingredient-based Group Recommender for Recipes (IGR2)

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :John Lindblad; Jonas Meddeb; [2022-02-16]
    Nyckelord :recommender systems; data science; user-generated content; contentbased filtering; singular value decomposition; recipes; food; group recommender systems;

    Sammanfattning : The number of food recipe options in modern society is vast and growing. While often being considered positive, the abundant options also lead to the so-called paradox of choice, i.e. that more options can lead to less happiness. LÄS MER


    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Santa Daniela Kanaska; [2022]
    Nyckelord :personalization; beauty tech; Artificial Intelligence; Recommender systems; AI ethics; data security; teknik för personliga hudvårdsråd; skönhetsteknik; Artificiell Intelligens; Rekommendationssystem; AI-etik; datasäkerhet;

    Sammanfattning : The researcher takes a user-centric empirical approach to estimate different consumer group participant views on the personalization technology adoption within the skincare industry. In addition, the study aims to highlight the main identified opportunities and concerns that users associate with the personalized technology solutions within the industry, such as skincare and product quizzes, in-depth questionnaires, smart skin analysis tools, and others. LÄS MER

  3. 3. Evaluating Cold-Start in Recommendation Systems Using a Hybrid Model Based on Factorization Machines and SBERT Embeddings

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Sabrina Chowdhury; [2022]
    Nyckelord :Natural Language Processing; Hybrid Recommender Systems; Cold-Start Problem; språkteknologi; hybrida rekommendationssystem; kallstartsproblemet;

    Sammanfattning : The item cold-start problem, which describes the difficulty of recommendation systems in recommending new items to users, remains a great challenge for recommendation systems that rely on past user-item interaction data. A popular technique in the current research surrounding the cold-start problem is the use of hybrid models that combine two or more recommendation strategies that may contribute with their individual advantages. LÄS MER

  4. 4. A graph database implementation of an event recommender system


    Författare :Alexander Olsson; [2022]
    Nyckelord :Event; Recommender system; Neo4j; Graph database;

    Sammanfattning : The internet is larger than ever and so is the amount of information on the internet.The average user on the internet has next to endless possibilities and choices whichcan cause information overload. Companies have therefore developed systems toguide their users to find the right product or object in the form of recommendersystems. LÄS MER

  5. 5. What's in a name? How the vocabulary of personalised playlists affects user's expectation and satisfactions in music streaming services

    Kandidat-uppsats, Jönköping University/JTH, Avdelningen för datateknik och informatik

    Författare :Nina Boksjö; Naomi Petricioiu; [2022]
    Nyckelord :Personalisation; Recommender Systems; Vocabulary; Spotify; Personalised Messages; Streaming Services; User Interface; Expectation; Satisfaction; User Experience;

    Sammanfattning : Background: The following study focuses on the area of personalisation within streaming services and how vocabulary of playlist names and categories affect expectations and satisfactions. The wording of personalised items is important to convey that content is directly made for a user, yet there are limited studies that explore what users anticipate and if the message conveys correct information to then lead to satisfaction. LÄS MER