Browsing by Author "Mendoza Rocha Marcelo Gabriel"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
- ItemAn Empirical Analysis of Rumor Detection on Microblogs with Recurrent Neural Networks(SPRINGER INTERNATIONAL PUBLISHING AG, 2019) Bugueno, Margarita; Sepulveda Villalobos Gabriel Andres; Mendoza Rocha Marcelo Gabriel; Meiselwitz, GThe popularity of microblogging websites makes them important for information dissemination. The diffusion of large volumes of fake or unverified information could emerge and spread producing damage. Due to the ever-increasing volume of data and the nature of complex diffusion, automatic rumor detection is a very challenging task. Supervised classification and other approaches have been widely used to identify rumors in social media posts. However, despite achieving competitive results, only a few studies have delved into the nature of the problem itself in order to identify key empirical factors that allow defining both the baseline models and their performance. In this work, we learn discriminative features from tweets content and propagation trees by following their sequential propagation structure. To do this we study the performance of a number of architectures based on recursive neural networks conditioning for rumor detection. In addition, to ingest tweets into each network, we study the effect of two different word embeddings schemes: Glove and Google news skip-grams. Results on the Twitter16 dataset show that model performance depends on many empirical factors and that some specific experimental configurations consistently drive to better results.
- ItemClaim Behavior over Time in Twitter(SPRINGER INTERNATIONAL PUBLISHING AG, 2019) Weiss, Fernanda; Espinoza, Ignacio; Hurtado Gonzalez Julio Andres; Mendoza Rocha Marcelo Gabriel; Meiselwitz, GSocial media is the primary source of information for many people around the world, not only to know about their families and friends but also to read about news and trends in different areas of interest. Fake News or rumors can generate big problems of misinformation, being able to change the mindset of a large group of people concerning a specific topic. Many companies and researchers have put their efforts into detecting these rumors with machine learning algorithms creating reports of the influence of these "news" in social media (https://www.knightfoundation.org/reports/disinformation-fake-news-and-influence-campaigns-on-twitter). Only a few studies have been made in detecting rumors in real-time, considering the first hours of propagation. In this work, we study the spread of a claim, analyzing different characteristics and how propagation patterns behave in time. Experiments show that rumors have different behaviours that can be used to classify them within the first hours of propagation.
- ItemGENE: Graph generation conditioned on named entities for polarity and controversy detection in social media(ELSEVIER SCI LTD, 2020) Mendoza Rocha Marcelo Gabriel; Parra Santander Denis Alejandro; Soto Arriaza AlvaroMany of the interactions between users on social networks are controversial, specially in polarized environments. In effect, rather than producing a space for deliberation, these environments foster the emergence of users that disqualify the position of others. On news sites, comments on the news are characterized by such interactions. This is detrimental to the construction of a deliberative and democratic climate, stressing the need for automatic tools that can provide an early detection of polarization and controversy. We introduce GENE (graph generation conditioned on named entities), a representation of user networks conditioned on the named entities (personalities, brands, organizations) which users comment upon. GENE models the leaning that each user has concerning entities mentioned in the news. GENE graphs is able to segment the user network according to their polarity. Using the segmented network, we study the performance of two controversy indices, the existing Random Walks Controversy (RWC) and another one we introduce, Relative Closeness Controversy (RCC). These indices measure the interaction between the network's poles providing a metric to quantify the emergence of controversy. To evaluate the performance of GENE, we model the network of users of a popular news site in Chile, collecting data in an observation window of more than three years. A large-scale evaluation using GENE, on thousands of news, allows us to conclude that over 60% of user comments have a predictable polarity. This predictability of the user interaction scenario allows both controversy indices to detect a controversy successfully. In particular, our introduced RCC index shows satisfactory performance in the early detection of controversies using partial information collected during the first hours of the news event, with a sensitivity to the target class exceeding 90%.