Filters








59,181 Hits in 7.8 sec

Method for Aspect-Based Sentiment Annotation Using Rhetorical Analysis [chapter]

Łukasz Augustyniak, Krzysztof Rajda, Tomasz Kajdanowicz
2017 Lecture Notes in Computer Science  
We present a comprehensive set of techniques derived from Rhetorical Structure Theory and sentiment analysis to extract aspects from textual opinions and then build an abstractive summary of a set of opinions  ...  This paper fills a gap in aspect-based sentiment analysis and aims to present a new method for preparing and analysing texts concerning opinion and generating user-friendly descriptive reports in natural  ...  Fig. 1 : 1 The workflow for Rhetorical and Sentiment Analysis. Fig. 2 : 2 An exemplary Discourse Tree based on Rhetorical Structure Theory.  ... 
doi:10.1007/978-3-319-54472-4_72 fatcat:fdhzzm3cqvgmdbulr5szqsgzzq

Extracting Aspects Hierarchies using Rhetorical Structure Theory [article]

Łukasz Augustyniak, Tomasz Kajdanowicz, Przemysław Kazienko
2019 arXiv   pre-print
We present an unsupervised technique using Rhetorical Structure Theory and graph analysis.  ...  The method could be easily extended with a sentiment analysis model and used to describe sentiment on different levels of aspect granularity.  ...  innovation programme under the Marie Skłodowska-Curie grant agreement No. 691152 (RENOIR) and the Polish Ministry of Science and Higher Education fund for supporting internationally co-financed projects in  ... 
arXiv:1909.01800v1 fatcat:n5pwtmghgrggbm2utt3r5ba7cy

Sentiment-Based Ranking of Blog Posts Using Rhetorical Structure Theory [chapter]

Jose M. Chenlo, Alexander Hogenboom, David E. Losada
2013 Lecture Notes in Computer Science  
Rhetorical Structure Theory (RST) provides important information about the relative importance of the different text spans in a document.  ...  Our results show that RST provides valuable information about the discourse structure of the texts that can be used to make a more accurate ranking of documents in terms of their estimated sentiment in  ...  Rhetorical Structure Theory Discourse analysis is concerned with how meaning is built up in the larger communicative process.  ... 
doi:10.1007/978-3-642-38824-8_2 fatcat:o4x6hmmr6bdenh3y6sci5svtma

Better Document-level Sentiment Analysis from RST Discourse Parsing [article]

Parminder Bhatia and Yangfeng Ji and Jacob Eisenstein
2015 arXiv   pre-print
First, we show that reweighting discourse units according to their position in a dependency representation of the rhetorical structure can yield substantial improvements on lexicon-based sentiment analysis  ...  We show that the discourse analyses produced by Rhetorical Structure Theory (RST) parsers can improve document-level sentiment analysis, via composition of local information up the discourse tree.  ...  We therefore turn to a data-driven approach for combining sentiment analysis with rhetorical structure theory, based on recursive neural networks (Socher et Ψ i = tanh(K (r i ) n Ψ n(i) + K (r i )  ... 
arXiv:1509.01599v2 fatcat:b5jfxo47sjdsjkfjtfordourui

Better Document-level Sentiment Analysis from RST Discourse Parsing

Parminder Bhatia, Yangfeng Ji, Jacob Eisenstein
2015 Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing  
First, we show that reweighting discourse units according to their position in a dependency representation of the rhetorical structure can yield substantial improvements on lexicon-based sentiment analysis  ...  We show that the discourse analyses produced by Rhetorical Structure Theory (RST) parsers can improve document-level sentiment analysis, via composition of local information up the discourse tree.  ...  We therefore turn to a data-driven approach for combining sentiment analysis with rhetorical structure theory, based on recursive neural networks (Socher et Ψ i = tanh(K (r i ) n Ψ n(i) + K (r i )  ... 
doi:10.18653/v1/d15-1263 dblp:conf/emnlp/BhatiaJE15 fatcat:ahst7n7cybfyrjknl6myfgrcgi

Ontology-based Recognition of Rhetorical Figures

Miljana Mladenović
2016 Infotheca - Journal for Digital Humanities  
translation, but also for analysis of linguistic structures on different levels.  ...  Automatic recognition of rhetorical figures (similes, irony, sarcasm, humor, metaphors, etc.) is increasingly used in natural language processing tasks, primarily to improve sentiment classification, machine  ...  We also plan to use the proposed method in a process of building features in sentiment analysis in Serbian.  ... 
doi:10.18485/infotheca.2016.16.1_2.2 fatcat:nnjk5bpetndj3npec2bt3pbtnm

Rhetorical Structure Theory for polarity estimation: An experimental study

José M. Chenlo, Alexander Hogenboom, David E. Losada
2014 Data & Knowledge Engineering  
In this paper, we investigate the usefulness of Rhetorical Structure Theory in various Sentiment Analysis tasks on different types of information sources.  ...  Sentiment Analysis tools often rely on counts of sentiment-carrying words, ignoring structural aspects of content.  ...  Taken as a whole, the body of work on discourse analysis for SA demonstrates the viability of using rhetorical structure.  ... 
doi:10.1016/j.datak.2014.07.009 fatcat:t7ne7psdlbbenapfyjqwn7ntem

Detecting Disagreement in Conversations using Pseudo-Monologic Rhetorical Structure

Kelsey Allen, Giuseppe Carenini, Raymond Ng
2014 Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)  
In this analysis we present a crowd-sourced annotated corpus for topic level disagreement detection in Slashdot, showing that disagreement detection in this domain is difficult even for humans.  ...  We then proceed to show that a new set of features determined from the rhetorical structure of the conversation significantly improves the performance on disagreement detection over a baseline consisting  ...  Features for Disagreement Detection The features we use in our experiments combine information from conversational structure, rhetorical relations, sentiment features, n-gram models, Slashdot meta-features  ... 
doi:10.3115/v1/d14-1124 dblp:conf/emnlp/AllenCN14 fatcat:kykjwx7j7zhjrijgjs7oo4kvae

Humour in Customer Engagement on Chinese Social Media – A Rhetorical Perspective

Jing Ge
2017 European Journal of Tourism Research  
To overcome the limitations of widely adopted sentiment analysis approaches, a crowdsourced sentiment analysis was used to code customer sentiment.  ...  A mixed approach to taxonomy development, including three-phase data analysis, was used.  ... 
doi:10.54055/ejtr.v15i.270 fatcat:y2tebre75reundczc5qavjisgi

Discourse structure and attitudinal valence of opinion words in sentiment extraction

Radoslava Trnavac, Maite Taboada
2014 LSA Annual Meeting Extended Abstracts  
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  ...  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  ...  In this paper, we use Rhetorical Structure Theory (Mann & Thompson 1988; Taboada & Mann 2006 ), a theory of discourse coherence.  ... 
doi:10.3765/exabs.v0i0.2391 fatcat:t6baz2eiezaubmhllhfhz2jq6y

Appraisal of Opinion Expressions in Discourse

2009 Lingvisticæ investigationes  
We propose a new annotation schema for a deep contextual opinion analysis using discourse relations.  ...  We present an analysis of opinion in texts based on a detailed semantic analysis of a wide class of expressions.  ...  We think there is still room for improvement in the field of sentiment analysis.  ... 
doi:10.1075/li.32.2.10ash fatcat:xitjimkt5fc2db3vgvtaxjaaiu

Construction of a Multilingual Annotated Corpus for Deeper Sentiment Understanding in Social Media

Yujie Lu, Kotaro Sakamoto, Hideyuki Shibuki, Tatsunori Mori
2017 Journal of Natural Language Processing  
Second, each rhetoric device maintains its own characteristics, influences global polarity in its own way, and has an inherent structure that helps to model the sentiment that it represents.  ...  Finally, based on observations and our analysis of our corpus, we present three key conclusions.  ...  Therefore, it is necessary to inspect the structure of each rhetoric device and clarify rhetoric influence on sentiment.  ... 
doi:10.5715/jnlp.24.205 fatcat:o64kfevr3ngihmysz7kckofznu

Discourse relations and evaluation

Radoslava Trnavac, Debopam Das, Maite Taboada
2016 Corpora  
of opinion words, and what impact the nucleus-satellite structure in RST has on the evaluation.  ...  Through a combination of Rhetorical Structure Theory or RST (Mann & Thompson, 1988) and Appraisal Theory (Martin & White, 2005) , we analyze how different discourse relations modify the evaluative content  ...  In the next section, we describe Rhetorical Structure Theory, a system of discourse relations that we use in our analysis to capture the relationship between discourse structure and evaluation.  ... 
doi:10.3366/cor.2016.0091 fatcat:fjdnjdzlqnedficbgydhoyckj4

Context incorporation using context — aware language features

Aggeliki Vlachostergiou, George Marandianos, Stefanos Kollias
2017 2017 25th European Signal Processing Conference (EUSIPCO)  
of contextual features, using data from two different in type and size datasets: the Movie Review Dataset (MR) and the Finegrained Sentiment Dataset (FSD).  ...  This paper investigates the problem of context incorporation into human language systems and particular in Sentiment Analysis (SA) systems.  ...  Rhetorical Structure Theory (RST): We use and extend the method presented in [5] , [23] to take advantage of the discourse relations in the text to compute sentiment values.  ... 
doi:10.23919/eusipco.2017.8081271 dblp:conf/eusipco/VlachostergiouM17 fatcat:qv5bjabvbra5bbcqdepy35yclq

Research on the Construction of Chinese Argument Corpus

Chen Zhang
2022 Open Journal of Modern Linguistics  
At the same time, the data set can also be used as a sentiment classification task.  ...  Faced with the serious shortage of annotated corpora used to train supervised learning algorithms in the field of argumentation mining, we created a reliable annotated corpus of Chinese argument structures  ...  Sentiment polarity is an important label in sentiment computing, and sentiment polarity analysis is the process of analyzing, processing, generalizing, and mathematically modeling subjective texts with  ... 
doi:10.4236/ojml.2022.121010 fatcat:com23prbsvgbra55e26egaumdq
« Previous Showing results 1 — 15 out of 59,181 results