Evaluating User Image Tagging Credibility
| Autor: | Adrian Iftene, Ioannis Kanellos, Adrian Popescu, Mihai Lupu, Alexandru Lucian Ginsca |
|---|---|
| Přispěvatelé: | Département informatique (INFO), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Laboratoire d'Intégration des Systèmes et des Technologies (LIST), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Vienna University of Technology (TU Wien), Faculty of Computer Science (University of Iasi - Al.I.Cuza) (UAIC Iasi), Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)) |
| Jazyk: | angličtina |
| Rok vydání: | 2015 |
| Předmět: |
Credibility evaluation dataset
Information retrieval Credible user retrieval Computer science Information seeking Source credibility 05 social sciences Supervised learning [INFO.INFO-WB]Computer Science [cs]/Web [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] User tagging credibility 02 engineering and technology Variety (cybernetics) [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] Web page Credibility 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing User classification Social image retrieval 0509 other social sciences 050904 information & library sciences Set (psychology) Image retrieval |
| Zdroj: | Proceedings CLEF 2015 : Conference and Labs of the Evaluation Forum CLEF 2015 : Conference and Labs of the Evaluation Forum CLEF 2015 : Conference and Labs of the Evaluation Forum, Sep 2015, Toulouse, France. pp.41-52, ⟨10.1007/978-3-319-24027-5_4⟩ Lecture Notes in Computer Science ISBN: 9783319240268 CLEF |
| DOI: | 10.1007/978-3-319-24027-5_4⟩ |
| Popis: | International audience; When looking for information on the Web, the credibility of the source plays an important role in the information seeking experience. While data source credibility has been thoroughly studied for Web pages or blogs, the investigation of source credibility in image retrieval tasks is an emerging topic. In this paper, we first propose a novel dataset for evaluating the tagging credibility of Flickr users built with the aim of covering a large variety of topics. We present the motivation behind the need for such a dataset, the methodology used for its creation and detail important statistics on the number of users, images and rater agreement scores. Next, we define both a supervised learning task in which we group the users in 5 credibility classes and a credible user retrieval problem. Besides a couple of credibility features described in previous works, we propose a novel set of credibility estimators, with an emphasis on text based descriptors. Finally, we prove the usefulness of our evaluation dataset and justify the performances of the proposed credibility descriptors by showing promising results for both of the proposed tasks. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|