scholarly journals Discourse structure and attitudinal valence of opinion words in sentiment extraction

2014 ◽  
Author(s):  
Radoslava Trnavac ◽  
Maite Taboada
Keyword(s):  
Sentiment Analysis ◽  
Discourse Structure ◽  
Extraction System ◽  
Reverse Polarity ◽  
Affective Content ◽  
Discourse Relations ◽  
Analysis System ◽  
Simon Fraser University

Taboada et al. (2008) propose a word-based method for extracting sentiment from text that relies on the most relevant parts of a text. The method predicts that opinion words found in the nuclei (more important parts) of a document are more significant for the overall sentiment, whereas opinion words found in the satellites (less important parts) only potentially interfere with the overall sentiment.  However, as pointed out by Taboada et al. (2008) and Narayanan et al. (2009), for certain discourse relations (for instance, Condition relations), the calculation of sentiment should involve both parts of the relation. Based on our analysis of the affective content expressed by automatically extracted discourse relations from the Simon Fraser University Corpus (Taboada 2008) and the Penn Discourse Treebank (Prasad et al. 2008), we propose to classify all the discourse relations into four categories: (1) relations that reverse polarity, (2) intensify polarity, (3) downtone polarity, or (4) produce no change in polarity.  We compare the performance of a sentiment analysis system (SO-CAL, Taboada et al. 2011) when opinion words are detected only in the nuclei with its performance when both parts of the relation are analyzed in combination with the opinion words. The results of the experiment show that extraction of both the nucleus and the satellite parts of texts does not improve the performance of a sentiment extraction system.

scholarly journals Enhanced Twitter Sentiment Analysis Using Hybrid Approach and by Accounting Local Contextual Semantic

2019 ◽  
Vol 29 (1) ◽  
pp. 1611-1625 ◽  
Author(s):  
Itisha Gupta ◽  
Nisheeth Joshi
Keyword(s):  
Sentiment Analysis ◽  
Feature Vector ◽  
Hybrid Approach ◽  
Classification Performance ◽  
Classification Model ◽  
Support Vector ◽  
Reverse Polarity ◽  
Analysis System ◽  
Accounting Procedure ◽  
Model Support

Abstract This paper addresses the problem of Twitter sentiment analysis through a hybrid approach in which SentiWordNet (SWN)-based feature vector acts as input to the classification model Support Vector Machine. Our main focus is to handle lexical modifier negation during SWN score calculation for the improvement of classification performance. Thus, we present naive and novel shift approach in which negation acts as both sentiment-bearing word and modifier, and then we shift the score of words from SWN based on their contextual semantic, inferred from neighbouring words. Additionally, we augment negation accounting procedure with a few heuristics for handling the cases in which negation presence does not necessarily mean negation. Experimental results show that the contextual-based SWN feature vector obtained through shift polarity approach alone led to an improved Twitter sentiment analysis system that outperforms the traditional reverse polarity approach by 2–6%. We validate the effectiveness of our hybrid approach considering negation on benchmark Twitter corpus from SemEval-2013 Task 2 competition.

scholarly journals Evaluation in Discourse: a Corpus-Based Study

2016 ◽  
Vol 7 (1) ◽  
pp. 1-49 ◽  
Author(s):  
Farah Benamara ◽  
Nicholas Asher ◽  
Yvette Yannick Mathieu ◽  
Vladimir Popescu ◽  
Baptiste Chardon
Keyword(s):  
Sentiment Analysis ◽  
Semantic Category ◽  
Discourse Structure ◽  
Annotation Scheme ◽  
Letters To The Editor ◽  
Discourse Representation Theory ◽  
Discourse Relations ◽  
Methodological Problems ◽  
Discourse Units ◽  
The Impact

This paper describes the CASOAR corpus, the first manually annotated corpus that explores the impact of discourse structure on sentiment analysis with a study of movie reviews in French and in English as well as letters to the editor in French. While annotating opinions at the expression, the sentence or the document level is a well-established task and relatively straightforward, discourse annotation remains difficult, especially for non-experts. Therefore, combining both annotations poses several methodological problems that we address here. We propose a multi-layered annotation scheme that includes: the complete discourse structure according to the Segmented Discourse Representation Theory, the opinion orientation of elementary discourse units and opinion expressions, and their associated features. We detail each layer, explore the interactions between them and discuss our results. In particular, we examine the correlation between discourse and semantic category of opinion expressions, the impact of discourse relations on both subjectivity and polarity analysis and the impact of discourse on the determination of the overall opinion of a document. Our results demonstrate that discourse is an important cue for sentiment analysis, at least for the corpus genres we have studied.

scholarly journals Enhanced concept-level sentiment analysis system with expanded ontological relations for efficient classification of user reviews

2021 ◽  
Author(s):  
Asad Khattak ◽  
Muhammad Zubair Asghar ◽  
Zain Ishaq ◽  
Waqas Haider Bangyal ◽  
Ibrahim A Hameed
Keyword(s):  
Sentiment Analysis ◽  
User Reviews ◽  
Analysis System

scholarly journals MoSa: A Modeling and Sentiment Analysis System for Mobile Application Big Data

Symmetry ◽  
2019 ◽  
Vol 11 (1) ◽  
pp. 115 ◽  
Author(s):  
Yaocheng Zhang ◽  
Wei Ren ◽  
Tianqing Zhu ◽  
Ehoche Faith
Keyword(s):  
Sentiment Analysis ◽  
Interaction Design ◽  
Mobile Application ◽  
Situational Awareness ◽  
Mobile Internet ◽  
The Public ◽  
Public Sentiment ◽  
High Altitude Area ◽  
Sentiment Dictionary ◽  
Analysis System

The development of mobile internet has led to a massive amount of data being generated from mobile devices daily, which has become a source for analyzing human behavior and trends in public sentiment. In this paper, we build a system called MoSa (Mobile Sentiment analysis) to analyze this data. In this system, sentiment analysis is used to analyze news comments on the THAAD (Terminal High Altitude Area Defense) event from Toutiao by employing algorithms to calculate the sentiment value of the comment. This paper is based on HowNet; after the comparison of different sentiment dictionaries, we discover that the method proposed in this paper, which use a mixed sentiment dictionary, has a higher accuracy rate in its analysis of comment sentiment tendency. We then statistically analyze the relevant attributes of the comments and their sentiment values and discover that the standard deviation of the comments’ sentiment value can quickly reflect sentiment changes among the public. Besides that, we also derive some special models from the data that can reflect some specific characteristics. We find that the intrinsic characteristics of situational awareness have implicit symmetry. By using our system, people can obtain some practical results to guide interaction design in applications including mobile Internet, social networks, and blockchain based crowdsourcing.

A Sentiment Analysis System to Improve Teaching and Learning

Computer ◽  
2017 ◽  
Vol 50 (5) ◽  
pp. 36-43 ◽  
Author(s):  
Sujata Rani ◽  
Parteek Kumar
Keyword(s):  
Sentiment Analysis ◽  
Teaching And Learning ◽  
Analysis System

scholarly journals Sentiment Analysis System in Big Data Environment

2018 ◽  
Vol 33 (3) ◽  
pp. 187-202
Author(s):  
Wint Nyein Chan ◽  
Thandar Thein
Keyword(s):  
Big Data ◽  
Sentiment Analysis ◽  
Data Environment ◽  
Analysis System
Sign in / Sign up

Export Citation Format

Share Document