Comparative Analysis of Globalisation Techniques for Medical Document Classification
Open Access
- 25 June 2023
- journal article
- research article
- Published by Journal of Soft Computing and Artificial Intelligence in Journal of Soft Computing and Artificial Intelligence
- Vol. 4 (1) , 7-14
Abstract
Medical document classification is one of the important topics of text mining. Globalisation techniques play a major role in text classification. It is also known that globalisation techniques play an important role in text classification. Our aim in the study is to conduct a detailed analysis on two data sets with English and Turkish content by using medical text summaries of Turkish articles. These datasets consist of Turkish and English text summaries of the same articles. To observe how successful local feature selection methods in the field of text classification affect the classification performance on these two equivalent data sets by applying different globalisation techniques. The feature selection methods used are CHI2, MI, OR, WLLR. Globalisation techniques are SUM, AVG, MAX. Classifiers are MNB, DT, and SVM.Keywords
This publication has 17 references indexed in Scilit:
- Deep and Machine Learning Approaches for Anomaly-Based Intrusion Detection of Imbalanced Network TrafficIEEE Sensors Letters, 2018
- Evaluating Insider Threat Detection Workflow Using Supervised and Unsupervised Learning2018
- Deep Learning approach for sentiment analysis of short texts2017
- User and entity behavior analytics for enterprise security2016
- Indoor Localization for Bluetooth Low Energy Devices Using Weighted Off-set Triangulation Algorithm2016
- Use of Machine Learning Algorithms with SIEM for Attack Prediction2014
- Experiences and Challenges in Enhancing Security Information and Event Management Capability Using Unsupervised Anomaly Detection2013
- Bridging the Gap: A Pragmatic Approach to Generating Insider Threat Data2013
- Enhancing Security Event Management Systems with Unsupervised Anomaly Detection2013
- Insider Threats to Cloud Computing: Directions for New Research Challenges2012