Context-sensitive learning methods for text categorization

Article Properties
Abstract
Cite
Cohen, William W., and Yoram Singer. “Context-Sensitive Learning Methods for Text Categorization”. ACM Transactions on Information Systems, vol. 17, no. 2, 1999, pp. 141-73, https://doi.org/10.1145/306686.306688.
Cohen, W. W., & Singer, Y. (1999). Context-sensitive learning methods for text categorization. ACM Transactions on Information Systems, 17(2), 141-173. https://doi.org/10.1145/306686.306688
Cohen WW, Singer Y. Context-sensitive learning methods for text categorization. ACM Transactions on Information Systems. 1999;17(2):141-73.
Journal Categories
Science
Mathematics
Instruments and machines
Electronic computers
Computer science
Science
Science (General)
Cybernetics
Information theory
Technology
Electrical engineering
Electronics
Nuclear engineering
Telecommunication
Technology
Technology (General)
Industrial engineering
Management engineering
Information technology
Description

Can machines learn to categorize text with human-like understanding? This paper investigates the effectiveness of context-sensitive learning methods in large text categorization problems. It evaluates two algorithms, RIPPER and sleeping-experts for phrases, which construct classifiers that consider the context of a word to influence its contribution to classification. While RIPPER and sleeping-experts differ in their approach to defining and combining contexts, they both demonstrate exceptional performance across a wide range of categorization tasks. The algorithms outperform previously applied learning methods, underscoring the value of incorporating contextual information. These results highlight the significance of context in machine learning and natural language processing. The findings have broad implications for improving the accuracy and efficiency of text categorization in various applications, from information retrieval to sentiment analysis and automated content tagging.

This article is highly relevant to ACM Transactions on Information Systems, which focuses on the design, development, and evaluation of information systems. By presenting and comparing two novel machine-learning algorithms for text categorization, the paper addresses a key challenge in information retrieval and knowledge management, aligning with the journal’s emphasis on innovative approaches to information processing.

Refrences
Citations
Citations Analysis
The first research to cite this article was titled An information filtering model on the Web and its application in JobAgent and was published in 2000. The most recent citation comes from a 2023 study titled An information filtering model on the Web and its application in JobAgent . This article reached its peak citation in 2014 , with 8 citations.It has been cited in 53 different journals, 9% of which are open access. Among related journals, the Expert Systems with Applications cited this research the most, with 6 citations. The chart below illustrates the annual citation trends for this article.
Citations used this article by year