Skip to main content

son doan

Followers

0

Following

1

Public Views

C. Michael Hall

University of Canterbury/Te Whare Wānanga o Waitaha

Oleg Yu Vorobyev

Siberian Federal University

Theodore Tsekeris

KEPE - Centre for Planning and Economic Research

Murat Cemal Yalcintan

Msgsu

University of Massachusetts Amherst

University of Westminster

Syafruddin Rauf

Hasanuddin University

IUU - Instituto Universitario de Urbanística University of Valladolid

Universidad de Valladolid

Bruce Appleyard

San Diego State University

Hercules Haralambides

Université Paris 1 - Panthéon-Sorbonne

Interests

Uploads

Papers by son doan

A Fuzzy-Based Approach for Text Representation in Text Categorization

Document representation is one of the most important tasks in text processing, especially in text... more Document representation is one of the most important tasks in text processing, especially in text categorization. This task has many applications that include document management, information retrieval, text routing, etc. In this paper, the author proposes a novel scheme for text representation based on fuzzy set theory. A new algorithm for choosing a term set that characterizes a document in the corpus is given under the view of fuzzy set. Experimental results applied to text categorization problem using the relevance feedback technique show that our proposed method reduced the number of dimensions and achieves higher performances compared to other baseline methods. In addition, it also produces results that compare favorably to the result achieved with the all vocabulary method

Multiple Concept Learning - A Novel Approach to Feature Selection in Text Categorization

Advances in Soft Computing, 2005

ABSTRACT

Dynamic Feature Selection in Text Classification

Lecture Notes in Control and Information Sciences, 2006

ABSTRACT

A General Fuzzy-Based Framework for Text Representation and Its Application to Text Categorization

Lecture Notes in Computer Science, 2006

In this paper we develop the general framework for text representation based on fuzzy set theory.

The Use of Multi-Criteria in Feature Selection to Enhance Text Categorization

Feature selection has been an interesting issue in text categorization up to now. Previous works ... more Feature selection has been an interesting issue in text categorization up to now. Previous works in feature selection often used filter model in which features, after ranked by a measure, are selected based on a given threshold. In this paper, we present a novel approach to feature selection based on multi-criteria of each feature. Instead of only one criterion, multi-criteria of a feature are used; and a procedure based on each threshold of feature selection is proposed. This framework seems to be suitable for text data and applied to text categorization. Experimental results on Reuters-21578 benchmark data show that our approach has a promising scheme and enhances the performance of a text categorization system.

Navigating the Information Storm

Methods and Case Studies, 2010

The role of roles in classifying annotated biomedical text

Proceedings of the Workshop on BioNLP 2007 Biological, Translational, and Clinical Language Processing - BioNLP '07, 2007

This paper investigates the roles of named entities (NE's) in annotated biomedical text classific... more This paper investigates the roles of named entities (NE's) in annotated biomedical text classification. In the annotation schema of BioCaster, a text mining system for public health protection, important concepts that reflect information about infectious diseases were conceptually analyzed with a formal ontological methodology. Concepts were classified as Types, while others were identified as being Roles. Types are specified as NE classes and Roles are integrated into NEs as attributes. We focus on the Roles of NEs by extracting and using them in different ways as features in the classifier. Experimental results show that: 1) Roles for each NE greatly helped improve performance of the system, 2) combining information about NE classes with their Roles contribute significantly to the improvement of performance. We discuss in detail the effect of each Role on the accuracy of text classification.

Enhancing Twitter Data Analysis with Simple Semantic Filtering: Example in Tracking Influenza-Like Illnesses

2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology, 2012

Systems that exploit publicly available user generated content such as Twitter messages have been... more Systems that exploit publicly available user generated content such as Twitter messages have been successful in tracking seasonal influenza. We developed a novel filtering method for Influenza-Like-Ilnesses (ILI)-related messages using 587 million messages from Twitter micro-blogs. We first filtered messages based on syndrome keywords from the BioCaster Ontology, an extant knowledge model of laymen's terms. We then filtered the messages according to semantic features such as negation, hashtags, emoticons, humor and geography. The data covered 36 weeks for the US 2009 influenza season from 30th August 2009 to 8th May 2010. Results showed that our system achieved the highest Pearson correlation coefficient of 98.46% (p-value<2.2e-16), an improvement of 3.98% over the previous state-of-the-art method. The results indicate that simple NLP-based enhancements to existing approaches to mine Twitter data can increase the value of this inexpensive resource.

An Empirical Study of Sections in Classifying Disease Outbreak Reports

Annals of Information Systems, 2010

ABSTRACT Identifying articles that relate to infectious diseases is a necessary step for any auto... more ABSTRACT Identifying articles that relate to infectious diseases is a necessary step for any automatic bio-surveillance system that monitors news articles from the Internet. Unlike scientific articles that are available in a strongly structured form, news articles are usually loosely structured. In this chapter, we investigate the importance of each section and the effect of section weighting on the performance of text classification. The experimental results show that (1) classification models using the headline and leading sentence achieve a high performance in terms of F-score compared to other parts of the article; (2) all section with bag-of-word representation (full text) achieves the highest recall; and (3) section weighting information can help to improve accuracy.

Syndromic Classification of Twitter Messages

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 2012

Recent studies have shown strong correlation between social networking data and national influenz... more Recent studies have shown strong correlation between social networking data and national influenza rates. We expanded upon this success to develop an automated text mining system that classifies Twitter messages in real time into six syndromic categories based on key terms from a public health ontology. 10-fold cross validation tests were used to compare Naive Bayes (NB) and Support Vector Machine (SVM) models on a corpus of 7431 Twitter messages. SVM performed better than NB on 4 out of 6 syndromes. The best performing classifiers showed moderately strong F1 scores: respiratory = 86.2 (NB); gastrointestinal = 85.4 (SVM polynomial kernel degree 2); neurological = 88.6 (SVM polynomial kernel degree 1); rash = 86.0 (SVM polynomial kernel degree 1); constitutional = 89.3 (SVM polynomial kernel degree 1); hemorrhagic = 89.9 (NB). The resulting classifiers were deployed together with an EARS C2 aberration detection algorithm in an experimental online system.

Using hedges to enhance a disease outbreak report text mining system

Proceedings of the Workshop on BioNLP - BioNLP '09, 2009

Content Analysis of Syndromic Twitter Data

Online Journal of Public Health Informatics, 2013

ABSTRACT Objective We present an annotation scheme developed to analyze syndromic Twitter data, a... more ABSTRACT Objective We present an annotation scheme developed to analyze syndromic Twitter data, and the results of its application to a set of respiratory syndrome-related tweets [1]. The scheme was designed to differentiate true positive tweets (where an individual is experiencing respiratory symptoms) from false positive tweets (where an individual is not experiencing respiratory symptoms), and to quantify more fine-grained information within the data. Introduction The popularity of Twitter, a social-networking service, creates the opportunity for researchers to collect large amounts of free, localizable data in real-time. Data takes the form of short, user-written messages, and has been employed for general syndromic surveillance [2] and surveillance of public attitudes toward the H1N1 flu outbreak [3]. Accessibility of tweets in real-time makes them particularly appropriate for use in early warning systems. Data collected through keyword search contains a significant amount of noise, however, annotation can help boost the signal for true positive tweets. Methods The annotation scheme was developed based on information relevant for early warning systems (e.g. who is experiencing symptoms, and when) as well as other information present in the tweets (e.g. aspirations regarding symptoms, or abuse of substances such as cough syrup). Categories included Experiencer: Self/Other, Temporality: Current/Non-Current, Sentiment: Positive/Negative, Information: Providing/Seeking, Language: Non-English, Aspiration, Hyperbole, and Substance Abuse. All categories with the exception of Language and Substance Abuse were defined in reference to diseases or symptoms. The scheme was applied to 1,100 respiratory syndrome-related tweets (544 false positive, 556 true positive) from a previously collected corpus of syndromic twitter data [2]. Inter-annotator agreement was calculated for 9% of the data (100 tweets). Results Inter-annotator agreement was generally good, however certain categories had lower scores. Categories for Experiencer, Temporality, Sentiment: Negative, Information: Providing, and Language all had Kappa values above .9, Sentiment: Positive, Aspiration, and Substance abuse had Kappa values above .7, and Information: Seeking and Hyperbole had Kappas above .6. There was good separation between true positive tweets and false positive tweets, especially for the Experiencer: Self, Temporality: Current, Sentiment: Negative, Aspiration, Hyperbole, and Substance Abuse categories (see Table). True positive data were more likely to belong to any category except Information: Providing, and Substance Abuse, in which cases false positive tweets had greater likelihood of category inclusion. Within the true positive data, we found that users were more likely to reference symptoms that they themselves were currently experiencing than they were to reference another person’s symptoms or non-current symptoms. Sentiment was largely negative, and there was significant use of aspiration and hyperbole. Conclusions Future work will apply the scheme to other syndromes, including constitutional, gastrointestinal, neurological, rash, and hemorrhagic. Table 1. Percentages of tweets included in each category. % True Positive Tweets % False Positive Tweets Experiencer: Self 98.2 0.4 Temporality: Current 98.7 0.2 Sentiment: Negative 79.7 1.7 Information: Providing 0.7 2.8 Language: Non-English 2.7 1.3 Aspiration 11.0 0.2 Hyperbole 18.3 0.2 Substance Abuse 1.3 8.1

Building and Using Geospatial Ontology in the BioCaster Surveillance System

Nature Precedings, 2008

ABSTRACT

Natural Language Processing in Biomedicine: A Unified System Architecture Overview

Methods in Molecular Biology, 2014

In contemporary electronic medical records much of the clinically important data-signs and sympto... more In contemporary electronic medical records much of the clinically important data-signs and symptoms, symptom severity, disease status, etc.-are not provided in structured data fi elds but rather are encoded in clinician-generated narrative text. Natural language processing (NLP) provides a means of unlocking this important data source for applications in clinical decision support, quality assurance, and public health. This chapter provides an overview of representative NLP systems in biomedicine based on a unifi ed architectural view. A general architecture in an NLP system consists of two main components: background knowledge that includes biomedical knowledge resources and a framework that integrates NLP tools to process text. Systems differ in both components, which we review briefl y. Additionally, the challenge facing current research efforts in biomedical NLP includes the paucity of large, publicly available annotated corpora, although initiatives that facilitate data sharing, system evaluation, and collaborative work between researchers in clinical NLP are starting to emerge.

An analysis of Twitter messages in the 2011 Tohoku Earthquake

Social media such as Facebook and Twitter have proven to be a useful resource to understand publi... more Social media such as Facebook and Twitter have proven to be a useful resource to understand public opinion towards real world events. In this paper, we investigate over 1.5 million Twitter messages (tweets) for the period 9th March 2011 to 31st May 2011 in order to track awareness and anxiety levels in the Tokyo metropolitan district to the 2011 Tohoku Earthquake and subsequent tsunami and nuclear emergencies. These three events were tracked using both English and Japanese tweets. Preliminary results indicated: 1) close correspondence between Twitter data and earthquake events, 2) strong correlation between English and Japanese tweets on the same events, 3) tweets in the native language play an important roles in early warning, 4) tweets showed how quickly Japanese people's anxiety returned to normal levels after the earthquake event. Several distinctions between English and Japanese tweets on earthquake events are also discussed. The results suggest that Twitter data can be used as a useful resource for tracking the public mood of populations affected by natural disasters as well as an early warning system.

BioCaster: detecting public health rumors with a Web-based text mining system

Bioinformatics/computer Applications in The Biosciences, 2008

BioCaster is an ontology-based text mining system for detecting and tracking the distribution of ... more BioCaster is an ontology-based text mining system for detecting and tracking the distribution of infectious disease outbreaks from linguistic signals on the Web. The system continuously analyzes documents reported from over 1700 RSS feeds, classifies them for topical relevance and plots them onto a Google map using geocoded information. The background knowledge for bridging the gap between Layman's terms and formal-coding systems is contained in the freely available BioCaster ontology which includes information in eight languages focused on the epidemiological role of pathogens as well as geographical locations with their latitudes/longitudes. The system consists of four main stages: topic classification, named entity recognition (NER), disease/location detection and event recognition. Higher order event analysis is used to detect more precisely specified warning signals that can then be notified to registered users via email alerts. Evaluation of the system for topic recognition and entity identification is conducted on a gold standard corpus of annotated news articles. Availability: The BioCaster map and ontology are freely available via a web portal at http://www.biocaster.org.

Applying semantic-based probabilistic context-free grammar to medical language processing – A preliminary study on parsing medication sentences

Journal of Biomedical Informatics, 2011

Semantic-based sublanguage grammars have been shown to be an efficient method for medical languag... more Semantic-based sublanguage grammars have been shown to be an efficient method for medical language processing. However, given the complexity of the medical domain, parsers using such grammars inevitably encounter ambiguous sentences, which could be interpreted by different groups of production rules and consequently result in two or more parse trees. One possible solution, which has not been extensively explored previously, is to augment productions in medical sublanguage grammars with probabilities to resolve the ambiguity. In this study, we associated probabilities with production rules in a semantic-based grammar for medication findings and evaluated its performance on reducing parsing ambiguity. Using the existing data set from 2009 i2b2 NLP (Natural Language Processing) challenge for medication extraction, we developed a semantic-based CFG (Context Free Grammar) for parsing medication sentences and manually created a Treebank of 4,564 medication sentences from discharge summaries. Using the Treebank, we derived a semantic-based PCFG (probabilistic Context Free Grammar) for parsing medication sentences. Our evaluation using a 10-fold cross validation showed that the PCFG parser dramatically improved parsing performance when compared to the CFG parser.

Towards role-based filtering of disease outbreak reports

Journal of Biomedical Informatics, 2009

This paper explores the role of named entities (NEs) in the classification of disease outbreak re... more This paper explores the role of named entities (NEs) in the classification of disease outbreak report. In the annotation schema of BioCaster, a text mining system for public health protection, important concepts that reflect information about infectious diseases were conceptually analyzed with a formal ontological methodology and classified into types and roles. Types are specified as NE classes and roles are integrated into NEs as attributes such as a chemical and whether it is being used as a therapy for some infectious disease. We focus on the roles of NEs and explore different ways to extract, combine and use them as features in a text classifier. In addition, we investigate the combination of roles with semantic categories of disease-related nouns and verbs. Experimental results using naïve Bayes and Support Vector Machine (SVM) algorithms show that: (1) roles in combination with NEs improve performance in text classification, (2) roles in combination with semantic categories of noun and verb features contribute substantially to the improvement of text classification. Both these results were statistically significant compared to the baseline ''raw text" representation. We discuss in detail the effects of roles on each NE and on semantic categories of noun and verb features in terms of accuracy, precision/recall and F-score measures for the text classification task.

Using Wikipedia for extracting hierarchy and building geo-ontology

International Journal of Web Information Systems, 2012

Purpose -This paper aims to serves two main purposes: First, it seeks to provide an overview of t... more Purpose -This paper aims to serves two main purposes: First, it seeks to provide an overview of the location hierarchy from the highest divisions (continents) to the lowest divisions (wards, villages) in reality and in the Wikipedia pages. Secondly, it aims to introduce an approach to building a geographical ontology from Wikipedia. Design/methodology/approach -The paper first reviews existing applications which extract information from Wikipedia and use it as a data resource to develop natural language processing tools. The paper also reviews the structure of Wikipedia pages which show the location's information. Based on the analysis, the paper then proposes an approach to extract location hierarchy as well as geographical characteristics for the geo-ontology. The approach also rebuilds the relations between locations in the ontology. Findings -Existing location name systems are mainly based on probabilistic locations, which are mined from the data and they lack the administrative relations between locations for full levels and all countries and territories. The literature review in geographical hierarchy and using Wikipedia for natural language processing tasks offers an approach to build a geographical ontology from Wikipedia pages. The proposed approach is believed to be the first which provides a full geo-ontology for all countries. Practical implications -The paper builds a geo-ontology with full levels for all countries and territories. The administrative relations between locations are needed for real-world applications. Originality/value -The comprehensive overview on existing work on geo-ontology provides a valuable reference for researchers and system developers in related research communities. The proposed approach to build a geographical ontology by using the Wikipedia offers a promising alternative to build a knowledge system from free online multi-language encyclopedia.

Classifying disease outbreak reports using n-grams and semantic features

International Journal of Medical Informatics, 2009

This paper explores the benefits of using ngrams and semantic features for the classification of ... more This paper explores the benefits of using ngrams and semantic features for the classification of disease outbreak reports, in the context of a text mining system -BioCaster -that identifies and tracks emerging infectious disease outbreaks from online news. We show that a combination of bag-of-words features, n-grams and semantic features, in conjunction with feature selection, improves classification accuracy at a statistically significant level when compared to previous work. A novel feature of the work reported in this paper is the use of a semantic tagger -the USAS tagger -to generate features. 2 The publicly accessible face of the BioCaster system is a visualization tool called Global Health Monitor.

A Fuzzy-Based Approach for Text Representation in Text Categorization

Document representation is one of the most important tasks in text processing, especially in text... more Document representation is one of the most important tasks in text processing, especially in text categorization. This task has many applications that include document management, information retrieval, text routing, etc. In this paper, the author proposes a novel scheme for text representation based on fuzzy set theory. A new algorithm for choosing a term set that characterizes a document in the corpus is given under the view of fuzzy set. Experimental results applied to text categorization problem using the relevance feedback technique show that our proposed method reduced the number of dimensions and achieves higher performances compared to other baseline methods. In addition, it also produces results that compare favorably to the result achieved with the all vocabulary method

Multiple Concept Learning - A Novel Approach to Feature Selection in Text Categorization

Advances in Soft Computing, 2005

ABSTRACT

Dynamic Feature Selection in Text Classification

Lecture Notes in Control and Information Sciences, 2006

ABSTRACT

A General Fuzzy-Based Framework for Text Representation and Its Application to Text Categorization

Lecture Notes in Computer Science, 2006

In this paper we develop the general framework for text representation based on fuzzy set theory.

The Use of Multi-Criteria in Feature Selection to Enhance Text Categorization

Feature selection has been an interesting issue in text categorization up to now. Previous works ... more Feature selection has been an interesting issue in text categorization up to now. Previous works in feature selection often used filter model in which features, after ranked by a measure, are selected based on a given threshold. In this paper, we present a novel approach to feature selection based on multi-criteria of each feature. Instead of only one criterion, multi-criteria of a feature are used; and a procedure based on each threshold of feature selection is proposed. This framework seems to be suitable for text data and applied to text categorization. Experimental results on Reuters-21578 benchmark data show that our approach has a promising scheme and enhances the performance of a text categorization system.

Navigating the Information Storm

Methods and Case Studies, 2010

The role of roles in classifying annotated biomedical text

Proceedings of the Workshop on BioNLP 2007 Biological, Translational, and Clinical Language Processing - BioNLP '07, 2007

This paper investigates the roles of named entities (NE's) in annotated biomedical text classific... more This paper investigates the roles of named entities (NE's) in annotated biomedical text classification. In the annotation schema of BioCaster, a text mining system for public health protection, important concepts that reflect information about infectious diseases were conceptually analyzed with a formal ontological methodology. Concepts were classified as Types, while others were identified as being Roles. Types are specified as NE classes and Roles are integrated into NEs as attributes. We focus on the Roles of NEs by extracting and using them in different ways as features in the classifier. Experimental results show that: 1) Roles for each NE greatly helped improve performance of the system, 2) combining information about NE classes with their Roles contribute significantly to the improvement of performance. We discuss in detail the effect of each Role on the accuracy of text classification.

Enhancing Twitter Data Analysis with Simple Semantic Filtering: Example in Tracking Influenza-Like Illnesses

2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology, 2012

Systems that exploit publicly available user generated content such as Twitter messages have been... more Systems that exploit publicly available user generated content such as Twitter messages have been successful in tracking seasonal influenza. We developed a novel filtering method for Influenza-Like-Ilnesses (ILI)-related messages using 587 million messages from Twitter micro-blogs. We first filtered messages based on syndrome keywords from the BioCaster Ontology, an extant knowledge model of laymen's terms. We then filtered the messages according to semantic features such as negation, hashtags, emoticons, humor and geography. The data covered 36 weeks for the US 2009 influenza season from 30th August 2009 to 8th May 2010. Results showed that our system achieved the highest Pearson correlation coefficient of 98.46% (p-value<2.2e-16), an improvement of 3.98% over the previous state-of-the-art method. The results indicate that simple NLP-based enhancements to existing approaches to mine Twitter data can increase the value of this inexpensive resource.

An Empirical Study of Sections in Classifying Disease Outbreak Reports

Annals of Information Systems, 2010

ABSTRACT Identifying articles that relate to infectious diseases is a necessary step for any auto... more ABSTRACT Identifying articles that relate to infectious diseases is a necessary step for any automatic bio-surveillance system that monitors news articles from the Internet. Unlike scientific articles that are available in a strongly structured form, news articles are usually loosely structured. In this chapter, we investigate the importance of each section and the effect of section weighting on the performance of text classification. The experimental results show that (1) classification models using the headline and leading sentence achieve a high performance in terms of F-score compared to other parts of the article; (2) all section with bag-of-word representation (full text) achieves the highest recall; and (3) section weighting information can help to improve accuracy.

Syndromic Classification of Twitter Messages

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 2012

Recent studies have shown strong correlation between social networking data and national influenz... more Recent studies have shown strong correlation between social networking data and national influenza rates. We expanded upon this success to develop an automated text mining system that classifies Twitter messages in real time into six syndromic categories based on key terms from a public health ontology. 10-fold cross validation tests were used to compare Naive Bayes (NB) and Support Vector Machine (SVM) models on a corpus of 7431 Twitter messages. SVM performed better than NB on 4 out of 6 syndromes. The best performing classifiers showed moderately strong F1 scores: respiratory = 86.2 (NB); gastrointestinal = 85.4 (SVM polynomial kernel degree 2); neurological = 88.6 (SVM polynomial kernel degree 1); rash = 86.0 (SVM polynomial kernel degree 1); constitutional = 89.3 (SVM polynomial kernel degree 1); hemorrhagic = 89.9 (NB). The resulting classifiers were deployed together with an EARS C2 aberration detection algorithm in an experimental online system.

Using hedges to enhance a disease outbreak report text mining system

Proceedings of the Workshop on BioNLP - BioNLP '09, 2009

Content Analysis of Syndromic Twitter Data

Online Journal of Public Health Informatics, 2013

ABSTRACT Objective We present an annotation scheme developed to analyze syndromic Twitter data, a... more ABSTRACT Objective We present an annotation scheme developed to analyze syndromic Twitter data, and the results of its application to a set of respiratory syndrome-related tweets [1]. The scheme was designed to differentiate true positive tweets (where an individual is experiencing respiratory symptoms) from false positive tweets (where an individual is not experiencing respiratory symptoms), and to quantify more fine-grained information within the data. Introduction The popularity of Twitter, a social-networking service, creates the opportunity for researchers to collect large amounts of free, localizable data in real-time. Data takes the form of short, user-written messages, and has been employed for general syndromic surveillance [2] and surveillance of public attitudes toward the H1N1 flu outbreak [3]. Accessibility of tweets in real-time makes them particularly appropriate for use in early warning systems. Data collected through keyword search contains a significant amount of noise, however, annotation can help boost the signal for true positive tweets. Methods The annotation scheme was developed based on information relevant for early warning systems (e.g. who is experiencing symptoms, and when) as well as other information present in the tweets (e.g. aspirations regarding symptoms, or abuse of substances such as cough syrup). Categories included Experiencer: Self/Other, Temporality: Current/Non-Current, Sentiment: Positive/Negative, Information: Providing/Seeking, Language: Non-English, Aspiration, Hyperbole, and Substance Abuse. All categories with the exception of Language and Substance Abuse were defined in reference to diseases or symptoms. The scheme was applied to 1,100 respiratory syndrome-related tweets (544 false positive, 556 true positive) from a previously collected corpus of syndromic twitter data [2]. Inter-annotator agreement was calculated for 9% of the data (100 tweets). Results Inter-annotator agreement was generally good, however certain categories had lower scores. Categories for Experiencer, Temporality, Sentiment: Negative, Information: Providing, and Language all had Kappa values above .9, Sentiment: Positive, Aspiration, and Substance abuse had Kappa values above .7, and Information: Seeking and Hyperbole had Kappas above .6. There was good separation between true positive tweets and false positive tweets, especially for the Experiencer: Self, Temporality: Current, Sentiment: Negative, Aspiration, Hyperbole, and Substance Abuse categories (see Table). True positive data were more likely to belong to any category except Information: Providing, and Substance Abuse, in which cases false positive tweets had greater likelihood of category inclusion. Within the true positive data, we found that users were more likely to reference symptoms that they themselves were currently experiencing than they were to reference another person’s symptoms or non-current symptoms. Sentiment was largely negative, and there was significant use of aspiration and hyperbole. Conclusions Future work will apply the scheme to other syndromes, including constitutional, gastrointestinal, neurological, rash, and hemorrhagic. Table 1. Percentages of tweets included in each category. % True Positive Tweets % False Positive Tweets Experiencer: Self 98.2 0.4 Temporality: Current 98.7 0.2 Sentiment: Negative 79.7 1.7 Information: Providing 0.7 2.8 Language: Non-English 2.7 1.3 Aspiration 11.0 0.2 Hyperbole 18.3 0.2 Substance Abuse 1.3 8.1

Building and Using Geospatial Ontology in the BioCaster Surveillance System

Nature Precedings, 2008

ABSTRACT

Natural Language Processing in Biomedicine: A Unified System Architecture Overview

Methods in Molecular Biology, 2014

In contemporary electronic medical records much of the clinically important data-signs and sympto... more In contemporary electronic medical records much of the clinically important data-signs and symptoms, symptom severity, disease status, etc.-are not provided in structured data fi elds but rather are encoded in clinician-generated narrative text. Natural language processing (NLP) provides a means of unlocking this important data source for applications in clinical decision support, quality assurance, and public health. This chapter provides an overview of representative NLP systems in biomedicine based on a unifi ed architectural view. A general architecture in an NLP system consists of two main components: background knowledge that includes biomedical knowledge resources and a framework that integrates NLP tools to process text. Systems differ in both components, which we review briefl y. Additionally, the challenge facing current research efforts in biomedical NLP includes the paucity of large, publicly available annotated corpora, although initiatives that facilitate data sharing, system evaluation, and collaborative work between researchers in clinical NLP are starting to emerge.

An analysis of Twitter messages in the 2011 Tohoku Earthquake

Social media such as Facebook and Twitter have proven to be a useful resource to understand publi... more Social media such as Facebook and Twitter have proven to be a useful resource to understand public opinion towards real world events. In this paper, we investigate over 1.5 million Twitter messages (tweets) for the period 9th March 2011 to 31st May 2011 in order to track awareness and anxiety levels in the Tokyo metropolitan district to the 2011 Tohoku Earthquake and subsequent tsunami and nuclear emergencies. These three events were tracked using both English and Japanese tweets. Preliminary results indicated: 1) close correspondence between Twitter data and earthquake events, 2) strong correlation between English and Japanese tweets on the same events, 3) tweets in the native language play an important roles in early warning, 4) tweets showed how quickly Japanese people's anxiety returned to normal levels after the earthquake event. Several distinctions between English and Japanese tweets on earthquake events are also discussed. The results suggest that Twitter data can be used as a useful resource for tracking the public mood of populations affected by natural disasters as well as an early warning system.

BioCaster: detecting public health rumors with a Web-based text mining system

Bioinformatics/computer Applications in The Biosciences, 2008

BioCaster is an ontology-based text mining system for detecting and tracking the distribution of ... more BioCaster is an ontology-based text mining system for detecting and tracking the distribution of infectious disease outbreaks from linguistic signals on the Web. The system continuously analyzes documents reported from over 1700 RSS feeds, classifies them for topical relevance and plots them onto a Google map using geocoded information. The background knowledge for bridging the gap between Layman's terms and formal-coding systems is contained in the freely available BioCaster ontology which includes information in eight languages focused on the epidemiological role of pathogens as well as geographical locations with their latitudes/longitudes. The system consists of four main stages: topic classification, named entity recognition (NER), disease/location detection and event recognition. Higher order event analysis is used to detect more precisely specified warning signals that can then be notified to registered users via email alerts. Evaluation of the system for topic recognition and entity identification is conducted on a gold standard corpus of annotated news articles. Availability: The BioCaster map and ontology are freely available via a web portal at http://www.biocaster.org.

Applying semantic-based probabilistic context-free grammar to medical language processing – A preliminary study on parsing medication sentences

Journal of Biomedical Informatics, 2011

Semantic-based sublanguage grammars have been shown to be an efficient method for medical languag... more Semantic-based sublanguage grammars have been shown to be an efficient method for medical language processing. However, given the complexity of the medical domain, parsers using such grammars inevitably encounter ambiguous sentences, which could be interpreted by different groups of production rules and consequently result in two or more parse trees. One possible solution, which has not been extensively explored previously, is to augment productions in medical sublanguage grammars with probabilities to resolve the ambiguity. In this study, we associated probabilities with production rules in a semantic-based grammar for medication findings and evaluated its performance on reducing parsing ambiguity. Using the existing data set from 2009 i2b2 NLP (Natural Language Processing) challenge for medication extraction, we developed a semantic-based CFG (Context Free Grammar) for parsing medication sentences and manually created a Treebank of 4,564 medication sentences from discharge summaries. Using the Treebank, we derived a semantic-based PCFG (probabilistic Context Free Grammar) for parsing medication sentences. Our evaluation using a 10-fold cross validation showed that the PCFG parser dramatically improved parsing performance when compared to the CFG parser.

Towards role-based filtering of disease outbreak reports

Journal of Biomedical Informatics, 2009

This paper explores the role of named entities (NEs) in the classification of disease outbreak re... more This paper explores the role of named entities (NEs) in the classification of disease outbreak report. In the annotation schema of BioCaster, a text mining system for public health protection, important concepts that reflect information about infectious diseases were conceptually analyzed with a formal ontological methodology and classified into types and roles. Types are specified as NE classes and roles are integrated into NEs as attributes such as a chemical and whether it is being used as a therapy for some infectious disease. We focus on the roles of NEs and explore different ways to extract, combine and use them as features in a text classifier. In addition, we investigate the combination of roles with semantic categories of disease-related nouns and verbs. Experimental results using naïve Bayes and Support Vector Machine (SVM) algorithms show that: (1) roles in combination with NEs improve performance in text classification, (2) roles in combination with semantic categories of noun and verb features contribute substantially to the improvement of text classification. Both these results were statistically significant compared to the baseline ''raw text" representation. We discuss in detail the effects of roles on each NE and on semantic categories of noun and verb features in terms of accuracy, precision/recall and F-score measures for the text classification task.

Using Wikipedia for extracting hierarchy and building geo-ontology

International Journal of Web Information Systems, 2012

Purpose -This paper aims to serves two main purposes: First, it seeks to provide an overview of t... more Purpose -This paper aims to serves two main purposes: First, it seeks to provide an overview of the location hierarchy from the highest divisions (continents) to the lowest divisions (wards, villages) in reality and in the Wikipedia pages. Secondly, it aims to introduce an approach to building a geographical ontology from Wikipedia. Design/methodology/approach -The paper first reviews existing applications which extract information from Wikipedia and use it as a data resource to develop natural language processing tools. The paper also reviews the structure of Wikipedia pages which show the location's information. Based on the analysis, the paper then proposes an approach to extract location hierarchy as well as geographical characteristics for the geo-ontology. The approach also rebuilds the relations between locations in the ontology. Findings -Existing location name systems are mainly based on probabilistic locations, which are mined from the data and they lack the administrative relations between locations for full levels and all countries and territories. The literature review in geographical hierarchy and using Wikipedia for natural language processing tasks offers an approach to build a geographical ontology from Wikipedia pages. The proposed approach is believed to be the first which provides a full geo-ontology for all countries. Practical implications -The paper builds a geo-ontology with full levels for all countries and territories. The administrative relations between locations are needed for real-world applications. Originality/value -The comprehensive overview on existing work on geo-ontology provides a valuable reference for researchers and system developers in related research communities. The proposed approach to build a geographical ontology by using the Wikipedia offers a promising alternative to build a knowledge system from free online multi-language encyclopedia.

Classifying disease outbreak reports using n-grams and semantic features

International Journal of Medical Informatics, 2009

This paper explores the benefits of using ngrams and semantic features for the classification of ... more This paper explores the benefits of using ngrams and semantic features for the classification of disease outbreak reports, in the context of a text mining system -BioCaster -that identifies and tracks emerging infectious disease outbreaks from online news. We show that a combination of bag-of-words features, n-grams and semantic features, in conjunction with feature selection, improves classification accuracy at a statistically significant level when compared to previous work. A novel feature of the work reported in this paper is the use of a semantic tagger -the USAS tagger -to generate features. 2 The publicly accessible face of the BioCaster system is a visualization tool called Global Health Monitor.