Improving kNN Text Categorization by Removing Outliers from Training Set
نویسندگان
چکیده
We show that excluding outliers from the training data significantly improves kNN classifier, which in this case performs about 10% better than the best know method—Centroid-based classifier. Outliers are the elements whose similarity to the centroid of the corresponding category is below a threshold.
منابع مشابه
Svm Based Improvement in Knn for Text Categorization
ABSTRACTIn today‟s library science, information and computer science, online text classification or text categorization is a huge complication. [1]With the enormous growth of online information and data, text categorization has become one of the crucial techniques for handling and standardizing text data. Various learning algorithms have been applied on text for categorization. On the basis of ...
متن کاملUsing cellular automata for improving knn based spam filtering
As rapid growth over the Internet nowadays, electronic mail (e-mails) has become a popular communication tool. However, junk mail also, known as spam has increasingly become a part of life for users as well as internet service providers. To address this problem, many solutions have been proposed in the last decade. Currently, content-based anti-spam filtering methods are an important issue; the...
متن کاملA ME Model Based on Feature Template for Chinese Text Categorization
With entering into information society and the Internet developing rapidly, people could acquire more and more information. How to utilize Internet information efficiently and promptly, has became a hotspot in information technology. Text categorization is an important component to help getting useful message from tremendous amount of vast information. And it assigns new documents to pre-define...
متن کاملML-KNN: A lazy learning approach to multi-label learning
Multi-label learning originated from the investigation of text categorization problem, where each document may belong to several predefined topics simultaneously. In multi-label learning, the training set is composed of instances each associated with a set of labels, and the task is to predict the label sets of unseen instances through analyzing training instances with known label sets. In this...
متن کاملAn effective refinement strategy for KNN text classifier
Due to the exponential growth of documents on the Internet and the emergent need to organize them, the automated categorization of documents into predefined labels has received an ever-increased attention in the recent years. A wide range of supervised learning algorithms has been introduced to deal with text classification. Among all these classifiers, K-Nearest Neighbors (KNN) is a widely use...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2006