Feature Engineering for Text Classification

By Sam Scott, Stan Matwin. 1999

How researchers see this paper

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

Citations in the corpus

Large-Scale Hierarchical Text Classification with Recursively Regularized Deep Graph-CNN (2018, background): “Different kinds of feature engineering, such as none-phrases or key-phrases, were shown no significant improvement on themselves, while the majority voting over the results of different features are significantly better [36].”
Feature selection for text classification: A review (2018, background): “However, combining classifiers based on different representations do bring some benefit in terms of accuracy [81].”
Applying LDA Topic Modeling in Communication Research: Toward a Valid and Reliable Methodology (2018, background): “While punctuation may bear important semantic information for human readers of a text, it is usually regarded as undesirable and uninformative in automatic text analyses based on the bag-of-words approach (e.g., Scott & Matwin, 1999, p. 379).”
Efficient phrase-based document indexing for Web document clustering (2004, methodology): “The methods used for text clustering includes decision trees [5], [6], [7], [8], statistical analysis [9], [10], [6], neural nets [11], inductive logic programming [12], [13], and rule-based systems [14], [15] among others.”
Effective Pattern Discovery for Text Mining (2012, background): “This hypothesis has not fared too well in the history of IR [19], [40], [41].”
Classifying Software Changes: Clean or Buggy? (2008, methodology): “Our change classification approach is programming language independent since we use a bag-of-words method [45] for generating features from the source code.”
Information Retrieval for E-Discovery (2013, background): “should the resulting feature set be transformed before it is used [123]? Two types of feature transformations are possible: feature selection (as when removing stopwords) and more general feature transformation (as when performing latent semantic indexing).”
Dependency Tree Kernels for Relation Extraction (2004, background): “Much time is spent on the task of feature engineering – searching for the optimal feature set either manually by consulting domain experts or automatically through feature induction and selection (Scott and Matwin, 1999).”
FeatureInsight: Visual support for error-driven feature ideation in text classification (2015, background): “A common feature engineering approach for text is “bag-ofwords” or n-grams [24], [25].”