Text Classification Using Association Rules, Dependency Pruning and Hyperonymization

Yannis Haralambous (1, 2) , Philippe Lenca (1, 3)

1 Lab-STICC_TB_CID_DECIDE
2 INFO - Département informatique
3 LUSSI - Département Logique des Usages, Sciences sociales et Sciences de l'Information

We present new methods for pruning and enhancing item- sets for text classification via association rule mining. Pruning methods are based on dependency syntax and enhancing methods are based on replacing words by their hyperonyms of various orders. We discuss the impact of these methods, compared to pruning based on tfidf rank of words.

Mots clés: Association Rules; Natural Language Processing; Dependency Syntax; Hyperonymization

Domaines: Interface homme-machine [cs.HC]; Ordinateur et société [cs.CY]; Réseaux et télécommunications [cs.NI]

Yannis Haralambous, Philippe Lenca. Text Classification Using Association Rules, Dependency Pruning and Hyperonymization. DMNLP 2014: Workshop on Interactions between Data Mining and Natural Language Processing, Sep 2014, Nancy, France. pp.65-80. ⟨hal-01058330⟩