A Novel Auto-Annotation Technique for Aspect Level Sentiment Analysis
作者机构：Department of Computer SciencesBahria UniversityLahore Campus54000Pakistan Computer and Information Science DepartmentUniversity TeknologiPetronas32610Malaysia
出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)
年 卷 期：2022年第70卷第3期
页 面：4987-5004页
核心收录：
学科分类：0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学]
基 金：The authors would like to express their most profound gratitude towards Mr. Umar Shoukat Mr. Muneeb Fazal Mr. Burhan Ul Haq Zahir and Ms. Rabbia Abrar for their valuable time and efforts for helping us in data collection and in the annotation process
主 题：Machine learning natural language processing annotation semi-annotated technique reviews annotation text annotation corpus annotation
摘 要：In machine learning,sentiment analysis is a technique to find and analyze the sentiments hidden in the *** sentiment analysis,annotated data is a basic ***,this data is manually *** annotation is time consuming,costly and laborious *** overcome these resource constraints this research has proposed a fully automated annotation technique for aspect level sentiment *** is created from the reviews of ten most popular songs on *** of five aspects—voice,video,music,lyrics and song,are *** N-Gram based technique is *** dataset consists of 369436 reviews that took 173.53 s to annotate using the proposed technique while this dataset might have taken approximately 2.07 million seconds(575 h)if it was annotated *** the validation of the proposed technique,a sub-dataset—Voice,is annotated manually as well as with the proposed ***’s Kappa statistics is used to evaluate the degree of agreement between the two *** high Kappa value(i.e.,0.9571%)shows the high level of agreement between the *** validates that the quality of annotation of the proposed technique is as good as manual annotation even with far less computational *** research also contributes in consolidating the guidelines for the manual annotation process.
维普期刊数据库