Centrality Measures from Complex Networks in Active Learning
In this paper, we present some preliminary results indicating that Complex Network properties may be useful to improve performance of Active Learning algorithms. In fact, centrality measures derived from networks generated from the data allow ranking the instances to find out the best ones to be presented to a human expert for manual classification. We discuss how to rank the instances based on the network vertex properties of closeness and betweenness. Such measures, used in isolation or combined, enable identifying regions in the data space that characterize prototypical or critical examples in terms of the classification task. Results obtained on different data sets indicate that, as compared to random selection of training instances, the approach reduces error rate and variance, as well as the number of instances required to reach representatives of all classes.
KeywordsComplex networks Active learning Text mining
Unable to display preview. Download preview PDF.
- 1.Berry, M.: Survey of Text Mining: Clustering, Classification, and Retrieval. Springer, Heidelberg (2003)Google Scholar
- 2.Minghim, R., Levkowitz, H.: Visual mining of text collections, Tutorial Notes. In: Proc. of EUROGRAPHICS 2007, Computer Graphics Forum, pp. 929–1021 (2007)Google Scholar
- 3.Settles, B.: Active learning literature survey. Computer Sciences Technical Report 1648, University of Wisconsin–Madison (2009)Google Scholar
- 6.Engelson, S., Dagan, I.: Minimizing manual annotation cost in supervised training from corpora. In: Proceedings of the 34th annual meeting on Association for Computational Linguistics, Morristown, NJ, USA, pp. 319–326. Association for Computational Linguistics (1996)Google Scholar
- 7.Hwa, R.: Sample selection for statistical grammar induction. In: Proceedings of EMNLP/VLC 2000, pp. 45–52 (2000)Google Scholar
- 9.Hoi, S., Jin, R., Lyu, M.: Large-scale text categorization by batch mode active learning. In: WWW 2006: Proceedings of the 15th international conference on World Wide Web, pp. 633–642. ACM, New York (2006)Google Scholar
- 14.Motta, R., Almeida, L.J., Lopes, A.A.: Probabilistic similarity based networks for exploring communities. In: I Workshop on Web and Text Intelligence (SBIA-WTI 2008), Salvador, Brasil, pp. 1–8 (2008) (in Portuguese)Google Scholar
- 15.Baeza-Yates, R.A., Ribeiro-Neto, B.A.: Modern Information Retrieval. ACM Press/Addison-Wesley (1999)Google Scholar