HumanISE - Indexed Articles in Conferences

Permanent URI for this collection

http://localhost:4000/handle/123456789/142

Browse

Browsing HumanISE - Indexed Articles in Conferences by Author "5448"
  • Item
    FEUP at TREC 2017 OpenSearch Track Graph-Based Models for Entity-Oriented
    ( 2017) José Luís Devezas ; Carla Lopes ; Sérgio Nunes ; 5585 ; 6205 ; 5448
  • Item
    Merging Datasets for Hate Speech Classification in Italian
    ( 2018) Sérgio Nunes ; Fortuna,P ; Bonavita,I ; 5448
    This paper presents an approach to the shared task HaSpeeDe within Evalita 2018. We followed a standard machine learning procedure with training, validation, and testing phases. We considered word embedding as features and deep learning for classification. We tested the effect of merging two datasets in the classification of messages from Facebook and Twitter. We concluded that using data for training and testing from the same social network was a requirement to achieve a good performance. Moreover, adding data from a different social network allowed to improve the results, indicating that more generalized models can be an advantage.
  • Item
    Social Media and Information Consumption Diversity
    ( 2018) Sérgio Nunes ; José Luís Devezas ; 5448 ; 5585
    Social media platforms are having a profound impact on the so-called information ecosystem, specifically on how information is produced, distributed and consumed. Social media in particular has contributed to the rise of user generated content and consequently to a greater diversity in online content. On the other hand, social media networks, such as Twitter or Facebook, have become information management tools that allow users to setup and configure information sources to their particular interests. A Twitter user can handpick the sources he wishes to follow, thus creating a custom information channel. However, this opportunity to create personalized information channels effectively results in different consumption profiles? Is the information consumed by users through social media networks distinct from the information consumed though traditional mainstream media? In this work, we set out to investigate this question using Twitter as a case study. We prepare two samples of users, one based on a uniform random selection of user IDs, and another one based on a selection of mainstream media followers. We analyze the home timelines of the users in each sample, focusing on characterizing information consumption habits. We find that information consumption volume is higher, while diversity is consistently lower, for mainstream media followers when compared to random users. When analyzing daily behavior, however, the samples slightly approximate, while clearly maintaining a lower diversity for mainstream media followers and a higher diversity for random users. Copyright © 2018 for the individual papers by the papers’ authors.