Aspect Based Hierarchical System: A Fine-grained Sentiment Analysis System in Edge Computing

Opinions are ubiquitous in text, and readers of online text—from consumers to sports fans to news addicts to governments—can benefit from automatic methods that synthesize useful opinion-oriented information from the sea of data. In this chapter on opinion mining and sentiment analysis, we introduce an idealized, end-to-end opinion analysis system and describe its components. We present methods for classifying documents and text passages according to their sentiment as well as methods that perform more fine-grained extraction of opinion expressions, their holders and their targets. We also address supplementary tasks of opinion lexicon construction, opinion summarization, opinion-oriented question answering, multi-lingual sentiment analysis and compositional approaches to phrase-level sentiment analysis.

Download Full-text

A Supervised Fine-Grained Sentiment Analysis System for Online Reviews

Intelligent Automation & Soft Computing ◽

10.1080/10798587.2015.1012830 ◽

2015 ◽

Vol 21 (4) ◽

pp. 589-605 ◽

Cited By ~ 5

Author(s):

Hanxiao Shi ◽

Wenping Zhan ◽

Xiaojun Li

Keyword(s):

Sentiment Analysis ◽

Online Reviews ◽

Fine Grained ◽

Analysis System

Download Full-text

Fuzzy-Based Sentiment Analysis System for Analyzing Student Feedback and Satisfaction

10.20944/preprints201907.0006.v1 ◽

2019 ◽

Author(s):

Muhammad Zubair Asghar ◽

Ikram Ullah ◽

Shahab Shamshirband ◽

Fazal Masud Kundi ◽

Ammara Habib

Keyword(s):

Sentiment Analysis ◽

State Of The Art ◽

Student Feedback ◽

Feedback Analysis ◽

Fine Grained ◽

Online Social Media ◽

Logic Module ◽

Data Collection And Analysis ◽

Analysis System ◽

Sentiment Score

The feedback collection and analysis has remained an important subject matter since long. The traditional techniques for student feedback analysis are based on questionnaire-based data collection and analysis. However, the student expresses their feedback opinions on online social media sites, which need to be analyzed. This study aims at the development of fuzzy-based sentiment analysis system for analyzing student feedback and satisfaction by assigning proper sentiment score to opinion words and polarity shifters present in the input reviews. Our technique computes the sentiment score of student feedback reviews and then applies fuzzy-logic module to analyze and quantify student’s satisfaction at the fine-grained level. The experimental results reveal that the proposed work has outperformed the baseline studies as well as state-of-the-art machine learning classifiers.

Download Full-text

How Translation Alters Sentiment

Journal of Artificial Intelligence Research ◽

10.1613/jair.4787 ◽

2016 ◽

Vol 55 ◽

pp. 95-130 ◽

Cited By ~ 37

Author(s):

Saif M. Mohammad ◽

Mohammad Salameh ◽

Svetlana Kiritchenko

Keyword(s):

Sentiment Analysis ◽

System A ◽

Sentiment Lexicon ◽

English Translations ◽

Dialectal Arabic ◽

Arabic And English ◽

Analysis System ◽

Arabic Sentiment Analysis ◽

Translation Systems ◽

Language Text

Sentiment analysis research has predominantly been on English texts. Thus there exist many sentiment resources for English, but less so for other languages. Approaches to improve sentiment analysis in a resource-poor focus language include: (a) translate the focus language text into a resource-rich language such as English, and apply a powerful English sentiment analysis system on the text, and (b) translate resources such as sentiment labeled corpora and sentiment lexicons from English into the focus language, and use them as additional resources in the focus-language sentiment analysis system. In this paper we systematically examine both options. We use Arabic social media posts as stand-in for the focus language text. We show that sentiment analysis of English translations of Arabic texts produces competitive results, w.r.t. Arabic sentiment analysis. We show that Arabic sentiment analysis systems benefit from the use of automatically translated English sentiment lexicons. We also conduct manual annotation studies to examine why the sentiment of a translation is different from the sentiment of the source word or text. This is especially relevant for building better automatic translation systems. In the process, we create a state-of-the-art Arabic sentiment analysis system, a new dialectal Arabic sentiment lexicon, and the first Arabic-English parallel corpus that is independently annotated for sentiment by Arabic and English speakers.

Download Full-text