Persona:
Araujo Serna, M. Lourdes

Cargando...
Foto de perfil
Dirección de correo electrónico
ORCID
0000-0002-7657-4794
Fecha de nacimiento
Proyectos de investigación
Unidades organizativas
Puesto de trabajo
Apellidos
Araujo Serna
Nombre de pila
M. Lourdes
Nombre

Resultados de la búsqueda

Mostrando 1 - 2 de 2
  • Publicación
    Analyzing information retrieval methods to recover broken web links
    (2011-06-19) Martínez Romo, Juan; Araujo Serna, M. Lourdes
    In this work we compare different techniques to automatically find candidate web pages to substitute broken links. We extract information from the anchor text, the content of the page containing the link, and the cache page in some digital library.The selected information is processed and submitted to a search engine. We have compared different information retrievalmethods for both, the selection of terms used to construct the queries submitted to the search engine, and the ranking of the candidate pages that it provides, in order to help the user to find the best replacement. In particular, we have used term frequencies, and a language model approach for the selection of terms; and cooccurrence measures and a language model approach for ranking the final results. To test the different methods, we have also defined a methodology which does not require the user judgments, what increases the objectivity of the results.
  • Publicación
    A Re-labeling Approach Based on Approximate Nearest Neighbors for Identifying Gambling Disorders in Social Media
    (Springer, 2023-09-11) Fabregat Marcos, Hermenegildo; Duque Fernández, Andrés; Araujo Serna, M. Lourdes; Martínez Romo, Juan; Agencia Estatal de Investigación (España); Instituto Mixto de Investigación-Escuela Nacional de Sanidad (IMIENS)
    This paper describes a novel approach based on Approximate Nearest Neighbors (ANN) techniques for modifying the granularity of the label schema in the training dataset of a classification task, from a user-based annotation to a message-based one. In particular, we tackle Task 1 of the CLEF 2022 eRisk Workshop which consists in the processing of messages written by Social Media users, in order to detect early signs of pathological gambling. Our proposal is based on the calculation of the nearest neighbors of the vectorial representations of the given messages, originally annotated at user-level. This way, we obtain a re-labeled training dataset in which messages from the same user can be either positive or negative. We then use this re-labeled dataset for performing the final classification on test instances. Compared to other systems participating in the task, our approach achieves the best average performance in the proposed evaluation frameworks, and shows to be the fastest one in terms of time needed to process the whole test dataset. This indicates that the proposed relabeling scheme allows us to capture more easily the textual information that leads to a correct detection of pathological gambling.