CIVILICA We Respect the Science
(ناشر تخصصی کنفرانسهای کشور / شماره مجوز انتشارات از وزارت فرهنگ و ارشاد اسلامی: ۸۹۷۱)

گواهی نمایه سازی مقاله Algorithm for Persian Text Sentiment Analysis in Correspondences on an E- Learning Social Website

عنوان مقاله: Algorithm for Persian Text Sentiment Analysis in Correspondences on an E- Learning Social Website
شناسه (COI) مقاله: JR_UJRSET-4-1_002
منتشر شده در فصلنامه پژوهش در علوم، مهندسی و تکنولوژی در سال ۱۳۹۵
مشخصات نویسندگان مقاله:

Anahid Rais Rohani - Department of Computer, College of Mechatronic, Karaj Branch, Islamic Azad University, Alborz, Iran
A zam Bastanfard - Department of Computer, College of Mechatronic, Karaj Branch, Islamic Azad University, Alborz, Iran

خلاصه مقاله:
By 2000, sentiment analysis had been only studied based on speech and changes in facialexpressions. Since then, studies have been focused on text. Concerning Persian text mining,studies have been conducted on the methods for extracting properties for classification andexamination of opinions on social websites with an aim to determine text polarity. Thepresent research was aimed to prepare and implement an algorithm for Persian textsentiment analysis based on the following six basic emotional states: happiness, sadness,fear, anger, surprise, and disgust. In this research, sentiment analysis was carried out usingthe unsupervised lexical method. Lexicons are divided into four categories, namely theemotional, boosters, negation, and stop lists. The algorithm was written in six different waysusing different properties. In the first method, the algorithm was capable of identifying anemotional word in a sentence. The sentiment of the sentence was determined based on thegiven emotional word. However, it should be noted that the text itself is also important forsentiment analysis because in addition to the emotional words, other factors (such asboosters and negating factors) are also present in the sentence and affect the text sentiment.Hence, the algorithm was enhanced in the subsequent methods to detect the boosters andnegating words. Results of running the algorithm using different methods indicated that thealgorithm accuracy increased with an increase in the number properties involved. In thesixth method, an algorithm capable of identifying emotional, boosters and negative wordswas applied to two data samples including sentences written by typical users and sentenceswritten by university students on an electronic learning social website. The accuracy of thealgorithm with 100 data samples from typical users and 100 data samples from universitystudents was 80% and 84%, respectively.

کلمات کلیدی:
sentiment analysisopinion miningtext mining

صفحه اختصاصی مقاله و دریافت فایل کامل: https://www.civilica.com/Paper-JR_UJRSET-JR_UJRSET-4-1_002.html