Beschreibung
The book is about text classification, more specifically news content classification. Large volume of information is produced in electronic form using different media. This information has to be organized for ease of access. Classification comes first so as to organize information and use it wisely. This book provides how to classify news items in to predefined set of categories. A lot of attempts has been done on English text classification but very few attempts are made on how to classify Amharic texts. Amharic is one of the largest Semitic language spoken by Ethiopian in Ethiopia and around the world. This book gives details on how to classify Amharic text news classification and forward the challenges and recommendations for doing so. Learning Vector Quantization (LVQ), which is one of efficient method among neural network algorithms, is used for Amharic text classification. The performance of the algorithm is measured for classifying Amharic text news. In general, the book is very important and it provides valuable information about Amharic language characteristics for computerization, Amharic text news classification, and LVQ among others.
Autorenporträt
I have completed my Masters degree in Information Science and my first degree in Information Technology Education at Addis Ababa University. I have thought for ten years at Bahir Dar University, Faculty of Computing. My areas of interest include: database, information storage and retrieval, and human computer interaction.
Herstellerkennzeichnung:
BoD - Books on Demand
In de Tarpen 42
22848 Norderstedt
DE
E-Mail: info@bod.de
