Sentiments and Opinions in Health-related Web messages
Published 1 September 2011
Marina Sokolova, Victoria Bobicev
Citations21
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The paper presents the annotation model, discusses characteristics of subjectivity annotations in health-related messages, and reports the results of the annotation agreement.
Abstract
In this work, we analyze sentiments and opinions expressed in user-written Web messages. The messages discuss healthrelated topics: medications, treatment, illness and cure, etc. Recognition of sentiments and opinions is a challenging task for humans as well as an automated text analysis. In this work, we apply both the approaches. The paper presents the annotation model, discusses characteristics of subjectivity annotations in health-related messages, and reports the results of the annotation agreement. For external evaluation of the labeling results, we apply Machine Learning methods on the annotated data and present the obtained results. 1
Keywords
Computer Science
Thumbs up?
6,987 Citations2002Bo Pang, Lillian Lee +1 more
This work considers the problem of classifying documents not by topic, but by overall sentiment, e.g., determining whether a review is positive or negative, and concludes by examining factors that make the sentiment classification problem more challenging.
Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification
2,026 Citations2007John Blitzer, Mark Dredze +1 more
This work extends to sentiment classification the recently-proposed structural correspondence learning (SCL) algorithm, reducing the relative error due to adaptation between domains by an average of 30% over the original SCL algorithm and 46% over a supervised baseline.
Journal of Clinical EpidemiologyHigh agreement but low kappa: II. Resolving the paradoxes
1,836 Citations1990Domenic V. Cicchetti, Alvan R. Feinstein
An omnibus index offers a single summary expression for a fourfold table of binary concordance among two observers and the paradoxes of kappa are desirable since they appropriately "penalize" inequalities in ppos and pneg.
Computers and the HumanitiesAnnotating Expressions of Opinions and Emotions in Language
1,770 Citations2005Janyce Wiebe, Theresa Wilson +1 more
The manual annotation process and the results of an inter-annotator agreement study on a 10,000-sentence corpus of articles drawn from the world press are presented.
Towards answering opinion questions
1,051 Citations2003Hong Yu, Vasileios Hatzivassiloglou
A Bayesian classifier for discriminating between documents with a preponderance of opinions such as editorials from regular news stories is presented, and three unsupervised, statistical techniques for the significantly harder task of detecting opinions at the sentence level are described.
Linguistics and PhilosophyContext Dependence, Disagreement, and Predicates of Personal Taste*
901 Citations2005Peter Lasersohn
Learning to identify emotions in text
668 Citations2008Carlo Strapparava, Rada Mihalcea
The construction of a large data set annotated for six basic emotions, ANGER, DISGUST, FEAR, JOY, SADNESS and SURPRISE, and several knowledge-based and corpusbased methods for the automatic identification of these emotions in text are proposed.
Comparing corpora using frequency profiling
587 Citations2000Paul Rayson, Roger Garside
The method can be used to discover key words in the corpora which differentiate one corpus from another and is shown to have applications in the study of social differentiation in the use of English vocabulary, profiling of learner English and document analysis in the software engineering process.
Using appraisal groups for sentiment analysis
562 Citations2005Casey Whitelaw, Navendu Garg +1 more
A new method for sentiment classification based on extracting and analyzing appraisal groups such as ``very good'' or ``not terribly funny'' is presented, based on several task-independent semantic taxonomies based on Appraisal Theory.
American Journal of Preventive MedicineInfodemiology and Infoveillance
417 Citations2011Günther Eysenbach
Using SentiWordNet for multilingual sentiment analysis
362 Citations2008Kerstin Denecke
The results show that working with standard technology and existing sentiment analysis approaches is a viable approach to sentiment analysis within a multilingual framework.
arXiv (Cornell University)Tracking point of view in narrative
307 Citations1994Janyce Wiebe
This paper presents an algorithm to develop an algorithm that tracks point of view on the basis of the regularities found in naturally occurring narrative, and describes the results of some preliminary empirical studies, which lend support to the algorithm.
arXiv (Cornell University)Sentiment Analysis in the News
211 Citations2013Alexandra Balahur, Ralf Steinberger +1 more
This work distinguishes three different possible views on newspaper articles ― author, reader and text, which have to be addressed differently at the time of analysing sentiment, and presents work on mining opinions about entities in English language news.
Crystal: Analyzing Predictive Opinions on the Web
111 Citations2007Soo-Min Kim, Eduard Hovy
An election prediction system based on web users’ opinions posted on an election prediction website, which significantly outperforms several baselines as well as a non-generalized n-gram approach and proposes a novel technique which generalizes n- gram feature patterns.
Lingvisticae InvestigationesAppraisal of Opinion Expressions in Discourse
89 Citations2009Nicholas Asher, Farah Benamara +1 more
A new annotation schema for a deep contextual opinion analysis using discourse relations is proposed and the distribution of categories in three different types of online corpora, movie reviews, Letters to the Editor and news reports is analyzed.
PubMedAnalysis of polarity information in medical text.
83 Citations2005Yun Niu, Xiaodan Zhu +2 more
The results show that generalization using the category information in the domain knowledge base Unified Medical Language System is effective in the task and combining linguistic features and domain knowledge leads to the highest accuracy.
Joint Research Centre (European Commission)Rethinking Sentiment Analysis in the News: from Theory to Practice and back
68 Citations2010Alexandra Balahur, STEINBERGER Ralf
The main tasks for news opinion mining are definition of the target; analysis of clearly marked opinion that is expressed explicitly, not needing interpretation or the use of world knowledge.
An agreement measure for determining inter-annotator reliability of human judgements on affective text
46 Citations2008Plaban Kr. Bhowmick, Pabitra Mitra +1 more
A new agreement measure inspired by Kappa coefficient is presented to compute inter-annotator reliability when the annotators have freedom to categorize a text into more than one class.
PubMedUsing outcome polarity in sentence extraction for medical question-answering.
39 Citations2006Yun Niu, Xiaodan Zhu +1 more
This work explores a multi-document summarization approach to automatically find information on clinical outcomes for questions about effects of using a medication to treat a disease, and shows that information onclinical outcomes improves the performance of summarization.
Journal of Medical Internet ResearchBiomedical Informatics Techniques for Processing and Analyzing Web Blogs of Military Service Members
26 Citations2010Sergiy Konovalov, Matthew Scotch +2 more
Natural language processing and automated information retrieval might potentially provide valuable tools for retrieving and analyzing military blog posts and uncovering military service members’ emotions and experiences of combat exposure.
Dublin City University Open Access Institutional Repository (Dublin City University)Exploring the use of paragraph-level annotations for sentiment analysis of financial blogs
23 Citations2009Paul Ferguson, Neil O’Hare +5 more
This paper explores the use of paragraph-level and document-level annotations, examining how additional information from paragraph- level annotations can be used to increase the accuracy of document- level sentiment classification.
RUA, Repositorio Institucional de la Universidad de Alicante (Universidad de Alicante)EmotiBlog: A Finer-Grained and More Precise Learning of Subjectivity Expression Models
20 Citations2010Estér Boldrini, Alexandra Balahur +2 more
The manner in which EmotiBlog is built is shown and the benefits it brings to the systems using it for training, through the experiments carried out on opinion mining and emotion detection, are demonstrated.
Learning opinions in user-generated web content
10 Citations2011M. S Okolova, G. L Apalme
Automatic Classification of Semantic Relations between Facts and Opinions
10 Citations2010Koji Murakami, Eric Nichols +7 more