ارسل ملاحظاتك

ارسل ملاحظاتك لنا







الرئيسية > Building An Arabic Sentiment L...>الوصف

Building An Arabic Sentiment Lexicon Using Semi Supervised Learning

المصدر: مجلة جامعة الملك سعود - علوم الحاسب والمعلومات
الناشر: جامعة الملك سعود
المؤلف الرئيسي: Mahyoub, Fawaz H.H. (Author)
مؤلفين آخرين: Siddiqui, Muazzam A. (Co-Author), Dahab, Mohamed Y. (Co-Author)
المجلد/العدد: مج26, ع4
محكمة: نعم
الدولة: السعودية
التاريخ الميلادي: 2014
الصفحات: 417 - 424
DOI: 10.33948/0584-026-004-007
ISSN: 1319-1578
رقم MD: 973360
نوع المحتوى: بحوث ومقالات
اللغة: الإنجليزية
قواعد المعلومات: science
مواضيع:
اللسانيات | صناعة المعاجم | اللغة العربية
كلمات المؤلف المفتاحية:
Sentiment Lexicon | Sentiment Analysis | Arabic Natural Language Processing | Text Mining | Semi Supervised Learnin
رابط المحتوى:
PDF (صورة)     
صورة الغلاف QR قانون
حفظ في:
المستخلص: Sentiment analysis is the process of determining a predefined sentiment from text written in a natural language with respect to the entity to which it is referring. A number of lexical resources are available to facilitate this task in English. One such resource is the Senti Word Net, which assigns sentiment scores to words found in the English Word Net. In this paper, we present an Arabic sentiment lexicon that assigns sentiment scores to the words found in the Arabic Word Net. Starting from a small seed list of positive and negative words, we used semi-supervised learning to propagate the scores in the Arabic Word Net by exploiting the synset relations. Our algorithm assigned a positive sentiment score to more than 800, a negative score to more than 600 and a neutral score to more than 6000 words in the Arabic Word Net. The lexicon was evaluated by incorporating it into a machine learning-based classifier. The experiments were conducted on several Arabic sentiment corpora, and we were able to achieve a 96% classification accuracy.
ISSN: 1319-1578

عناصر مشابهة


© 2024 المنظومة. جميع الحقوق محفوظة.