Phrase Based Amharic News Text Classification - Abebaw, Zeleke
32,99 €
inkl. MwSt.
Versandkostenfrei*
Versandfertig in 6-10 Tagen
  • Broschiertes Buch

The recent growth of ICT infrastructure in Ethiopia is resulting in an exponential increase of digital information in local languages including Amharic. Huge volumes of data are available in Amharic, which is observed on the growing online newspapers, websites, and digital storage's of Ethiopian News Agency. To tackle the agency s news text management problems, a number of researches have been conducted on automatic processing of Amharic news texts using bag-of-words feature representation. However, using single words as features could result in losing the intended meaning when the concept is…mehr

Andere Kunden interessierten sich auch für
Produktbeschreibung
The recent growth of ICT infrastructure in Ethiopia is resulting in an exponential increase of digital information in local languages including Amharic. Huge volumes of data are available in Amharic, which is observed on the growing online newspapers, websites, and digital storage's of Ethiopian News Agency. To tackle the agency s news text management problems, a number of researches have been conducted on automatic processing of Amharic news texts using bag-of-words feature representation. However, using single words as features could result in losing the intended meaning when the concept is created from two or more sequential words. Thus, in order to maintain this concept, a phrase based approach (using bigrams and trigrams) has been proposed and implemented in this research.The result shows that using bigram phrases,the best accuracy (95.3%) has been obtained at four news categories, followed by (81.3%)for eight categories and (72.01%) for twelve categories.On the other hand, for trigram phrase structures, the best accuracy was(72.9%)four news categories, followed by 69.7% for eight categories, and 56.4% for twelve categories. Thus,bigrams shows better accuracy than trigrams.
Autorenporträt
Mr. Zeleke Abebaw Kassa has received his B.Sc degree in Information Technology from Addis Ababa University in 2005 G.C. and his M.Sc.Degree in Information Science from the same University in 2010 G.C. Currently, he is a lecturer of Information Technology in the department of IT at Addis Ababa Science and Technology University.