Supervised and Traditional Term Weighting Methods for Automatic Text Categorization

By Man Lan, Chew Lim Tan, Jian Su, Yue Lu. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009

604 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Sentiment Analysis: A Comparative Study on Different Approaches☆ (2016, methodology): “Next, each domain dictionary was replenished with appraisal words of appropriate training collection that have the highest weight, calculated by the method of RF (Relevance Frequency) [15].”
N-gram IDF: A Global Term Weighting Scheme Based on Information Distance (2015, background): “Specialized global term weighting schemes like Inverse Corpus Frequency (ICF) [34], designed for analyzing text stream, and Relevant Frequency (RF) [23], for text classification, can also be alternatives in the target applications.”
Graph-based term weighting for text categorization (2015, methodology): “Initially, we introduce the traditional Bag-of-Words document representation and the corresponding frequency-based TF, TF-IDF term weighting criteria that can be derived by this model and have extensively been used in TC and most of the common text analytics tasks (e.g., IR, document clustering,…”
SIFT Meets CNN: A Decade Survey of Instance Retrieval (2016, background): “g., xI[124] and Residual IDF [125]. In text stream analysis and text classiﬁcation, task-speciﬁc global term weighting schemes such as Inverse Corpus Frequency (ICF) [126] and Relevant Frequency (RF) [127] have also proven to be effective. Despite JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST”