Repository logo

Browsing by Subject "user profiling"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • thumbnail.journal.alt
    Item type:Article, Access status: Open Access ,
    Application of multi-criteria analysis based on individual psychological profile for recommender systems
    (Wydawnictwa AGH, 2016) Rafalak, Maria; Granat, Janusz; Wierzbicki, Andrzej P.
    This paper presents a novel approach for user classification exploiting multicriteria analysis. This method is based on measuring the distance between an observation and its respective Pareto front. The obtained results show that the combination of the standard KNN classification and the distance from Pareto fronts gives satisfactory classification accuracy - higher than the accuracy obtained for each of these methods applied separately. Conclusions from this study may be applied in recommender systems where the proposed method can be implemented as the part of the collaborative filtering algorithm.
  • thumbnail.journal.alt
    Item type:Article, Access status: Open Access ,
    Building semantic user profile for polish web news portal
    (Wydawnictwa AGH, 2018) Misztal-Radecka, Joanna
    The aim of this research is to construct meaningful user profiles that are the most descriptive of user interests in the context of the media content that they browse. We use two distinct state-of-the-art numerical text-representation techniques: LDA topic modeling and Word2Vec word embeddings. We train our models on the collection of news articles in Polish and compare them with a model built on a general language corpus. We compare the performance of these algorithms on two practical tasks. First, we perform a qualitative analysis of the semantic relationships for similar article retrieval, and then we evaluate the predictive performance of distinct feature combinations for user gender classification. We apply the algorithms to the real-world dataset of Polish news service Onet. Our results show that the choice of text representation depends on the task - Word2Vec is more suitable for text comparison, especially for short texts such as titles. In the gender classification task, the best performance is obtained with a combination of features: topics from the article text and word embeddings from the title.