Sources of Evidence for Automatic Indexing of Political Texts

  • Mostafa Dehghani
  • Hosein Azarbonyad
  • Maarten Marx
  • Jaap Kamps
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9022)


Political texts on the Web, documenting laws and policies and the process leading to them, are of key importance to government, industry, and every individual citizen. Yet access to such texts is difficult due to the ever increasing volume and complexity of the content, prompting the need for indexing or annotating them with a common controlled vocabulary or ontology. In this paper, we investigate the effectiveness of different sources of evidence—such as the labeled training data, textual glosses of descriptor terms, and the thesaurus structure—for automatically indexing political texts. Our main findings are the following. First, using a learning to rank (LTR) approach integrating all features, we observe significantly better performance than previous systems. Second, the analysis of feature weights reveals the relative importance of various sources of evidence, also giving insight in the underlying classification problem. Third, a lean-and-mean system using only four features (text, title, descriptor glosses, descriptor term popularity) is able to perform at 97% of the large LTR model.


Automatical Indexing Political Texts Learning to Rank 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    EuroVoc. Multilingual thesaurus of the european union,
  2. 2.
    Iivonen, M.: Consistency in the selection of search concepts and search terms. IPM 31, 173–190 (1995)Google Scholar
  3. 3.
    Joachims, T.: Training linear svms in linear time. In: SIGKDD, pp. 217–226 (2006)Google Scholar
  4. 4.
    Nam, J., Kim, J., Loza Mencía, E., Gurevych, I., Fürnkranz, J.: Large-scale multi-label text classification - revisiting neural networks. In: Calders, T., Esposito, F., Hüllermeier, E., Meo, R. (eds.) ECML PKDD 2014, Part II. LNCS, vol. 8725, pp. 437–452. Springer, Heidelberg (2014)CrossRefGoogle Scholar
  5. 5.
    Pouliquen, B., Steinberger, R., Ignat, C.: Automatic annotation of multilingual text collections with a conceptual thesaurus. In: EUROLAN, pp. 9–28 (2003)Google Scholar
  6. 6.
    Ren, Z., Peetz, M.-H., Liang, S., van Dolen, W., de Rijke, M.: Hierarchical multi-label classification of social text streams. In: SIGIR, pp. 213–222 (2014)Google Scholar
  7. 7.
    Rousu, J., Saunders, C., Szedmak, S., Shawe-Taylor, J.: Kernel-based learning of hierarchical multilabel classification models. J. Mach. Learn. Res. 7, 1601–1626 (2006)zbMATHMathSciNetGoogle Scholar
  8. 8.
    Steinberger, R., Pouliquen, B., Widiger, A., Ignat, C., Erjavec, T., Tufis, D.: The JRC-Acquis: A multilingual aligned parallel corpus with 20+ languages. In: LREC, pp. 2142–2147 (2006)Google Scholar
  9. 9.
    Steinberger, R., Ebrahim, M., Turchi, M.: JRC EuroVoc indexer JEX-A freely available multi-label categorisation tool. In: LREC, pp. 798–805 (2012)Google Scholar
  10. 10.
    Xu, J., Li, H.: Adarank: A boosting algorithm for information retrieval. In: SIGIR, pp. 391–398 (2007)Google Scholar
  11. 11.
    Yang, Y., Gopal, S.: Multilabel classification with meta-level features in a learning-to-rank framework. Machine Learning 88(1-2), 47–68 (2012)CrossRefzbMATHMathSciNetGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Mostafa Dehghani
    • 1
  • Hosein Azarbonyad
    • 2
  • Maarten Marx
    • 2
  • Jaap Kamps
    • 1
  1. 1.Institute for Logic, Language and ComputationUniversity of AmsterdamNetherlands
  2. 2.Informatics InstituteUniversity of AmsterdamNetherlands

Personalised recommendations