Comparing Machine Learning and Information Retrieval-Based Approaches for Filtering Documents in a Parliamentary Setting
| Autor: | Luis Redondo-Expósito, Juan M. Fernández-Luna, Luis M. de Campos, Juan F. Huete |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Information retrieval
Parliament Computer science business.industry media_common.quotation_subject Document classification Context (language use) 02 engineering and technology computer.software_genre Machine learning Task (project management) 020204 information systems 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business computer media_common |
| Zdroj: | Lecture Notes in Computer Science ISBN: 9783319675817 SUM |
| DOI: | 10.1007/978-3-319-67582-4_5 |
| Popis: | We consider the problem of building a content-based recommender/filtering system in a parliamentary context which, given a new document to be recommended, can decide those Members of Parliament who should receive it. We propose and compare two different approaches to tackle this task, namely a machine learning-based method using automatic document classification and an information retrieval-based approach that matches documents and legislators’ representations. The information necessary to build the system is automatically extracted from the transcriptions of the speeches of the members of parliament within the parliament debates. Our proposals are experimentally tested for the case of the regional Andalusian Parliament at Spain. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|