MediConceptNet: An Affinity Score Based Medical Concept Network

In healthcare, information extraction is essential in building automatic domain-specific applications. Medical concepts and their semantic identification take an important role to develop a network for visualizing medical concepts and their relations. The challenge appears while available medical corpora are only in either unstructured or semi-structured forms. In the present paper, to overcome the challenge and consequently to construct a structured corpus, we apply a domain-specific lexicon, namely WordNet of Medical Event. Medical concepts assigned by this lexicon and their affinity score, polarity score, sense, and semantic features assist in identifying conceptual and sentiment relations from the corpus. The lexicon and all these features provide an essential support to analyze an unstructured corpus and represent it in a structured corpus which we term MediConceptNet: the medical concepts are connected with each other through the concerned features. A previously suggested network for the same purpose, e.g., SemNet, is only based on the semantic and affinity features. The semantic relations of the concepts can be successfully determined in three distinct ranges, e.g., 0 for no relation, 0-1 for partial relations, and 1 corresponding a full relation. To evaluate the data of MediConceptNet, we apply an agreement analysis provided by the Cohen’s kappa coefficient and achieve 0.66 agreement score, evaluating the comparative statistics of two medical practitioners working as manual an-

[1]  Erik Cambria,et al.  An Introduction to Concept-Level Sentiment Analysis , 2013, MICAI.

[2]  Dipankar Das,et al.  Lexical Resource for Medical Events: A Polarity Based Approach , 2015, 2015 IEEE International Conference on Data Mining Workshop (ICDMW).

[3]  Pierre Zweigenbaum,et al.  A Hybrid Approach for the Extraction of Semantic Relations from MEDLINE Abstracts , 2011, CICLing.

[4]  Erik T. Mueller,et al.  Open Mind Common Sense: Knowledge Acquisition from the General Public , 2002, OTM.

[5]  Yimin Wang,et al.  Towards Semi-automatic Ontology Building Supported by Large-Scale Knowledge Acquisition , 2006, AAAI Fall Symposium: Semantic Web for Collaborative Knowledge Acquisition.

[6]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[7]  Haixun Wang,et al.  Guest Editorial: Big Social Data Analysis , 2014, Knowl. Based Syst..

[8]  Erik Cambria,et al.  Sentiment Data Flow Analysis by Means of Dynamic Linguistic Patterns , 2015, IEEE Computational Intelligence Magazine.

[9]  Erik Cambria,et al.  Common Sense Knowledge Based Personality Recognition from Text , 2013, MICAI.

[10]  Erik Cambria,et al.  A graph-based approach to commonsense concept extraction and semantic similarity detection , 2013, WWW.

[11]  Björn W. Schuller,et al.  SenticNet 4: A Semantic Resource for Sentiment Analysis Based on Conceptual Primitives , 2016, COLING.

[12]  Jun'ichi Tsujii,et al.  GENIA corpus - a semantically annotated corpus for bio-textmining , 2003, ISMB.

[13]  Lorraine K. Tanabe,et al.  GENETAG: a tagged corpus for gene/protein named entity recognition , 2005, BMC Bioinformatics.

[14]  Erik M. van Mulligen,et al.  Using an ensemble system to improve concept extraction from clinical records , 2012, J. Biomed. Informatics.

[15]  Christiane Fellbaum,et al.  Medical WordNet: A New Methodology for the Construction and Validation of Information Resources for Consumer Health , 2004, COLING.

[16]  Andrea Esuli,et al.  SENTIWORDNET: A Publicly Available Lexical Resource for Opinion Mining , 2006, LREC.

[17]  Dipankar Das,et al.  WME: Sense, Polarity and Affinity based Concept Resource for Medical Events , 2016, GWC.

[18]  Hsin-Hsi Chen,et al.  Information retrieval with commonsense knowledge , 2006, SIGIR.

[19]  Ehsan Asgarian,et al.  Designing an Integrated Semantic Framework for Structured Opinion Summarization , 2014, ESWC.

[20]  Maite Taboada,et al.  Lexicon-Based Methods for Sentiment Analysis , 2011, CL.

[21]  Ramanathan V. Guha,et al.  Cyc: toward programs with common sense , 1990, CACM.

[22]  Catherine Havasi,et al.  Representing General Relational Knowledge in ConceptNet 5 , 2012, LREC.

[23]  John McCarthy,et al.  Programs with common sense , 1960 .

[24]  Lynda Tamine,et al.  Biomedical concept extraction based on combining the content-based and word order similarities , 2011, SAC.

[25]  Erik Cambria,et al.  Bridging the Gap between Structured and Unstructured Health-Care Data through Semantics and Sentics , 2011 .

[26]  A. Viera,et al.  Understanding interobserver agreement: the kappa statistic. , 2005, Family medicine.

[27]  James F. Allen,et al.  TRIPS and TRIOS System for TempEval-2: Extracting Temporal Information from Text , 2010, *SEMEVAL.

[28]  Bing Liu,et al.  Sentiment Analysis and Opinion Mining , 2012, Synthesis Lectures on Human Language Technologies.

[29]  Mehdi Embarek,et al.  Learning Patterns for Building Resources about Semantic Relations in the Medical Domain , 2008, LREC.

[30]  Nirmalie Wiratunga,et al.  Domain-Based Lexicon Enhancement for Sentiment Analysis , 2013, SMA@BCS-SGAI.

[31]  Erik Cambria,et al.  Common Sense Computing: From the Society of Mind to Digital Intuition and beyond , 2009, COST 2101/2102 Conference.