Please use this identifier to cite or link to this item: http://hdl.handle.net/10995/36860
Title: Towards Automatic Evaluation of Health-Related CQA Data
Authors: Beloborodov, A.
Braslavski, P.
Driker, M.
Браславский, П. И.
Белобородов, А. В.
Issue Date: 2014
Publisher: Springer Verlag
Citation: Beloborodov A. Towards Automatic Evaluation of Health-Related CQA Data / A. Beloborodov, P. Braslavski, M. Driker // Lecture Notes in Computer Science (5th International Conference of the CLEF Initiative, CLEF 2014). — Springer Verlag, 2014. — Vol. 8685 LNCS. — P. 7-18.
Abstract: The paper reports on evaluation of Russian community question answering (CQA) data in health domain. About 1,500 question-answer pairs were manually evaluated by medical professionals, in addition automatic evaluation based on reference disease-medicine pairs was performed. Although the results of the manual and automatic evaluation do not fully match, we find the method still promising and propose several improvements. Automatic processing can be used to dynamically monitor the quality of the CQA content and to compare different data sources. Moreover, the approach can be useful for symptomatic surveillance and health education campaigns.
Keywords: NATURAL LANGUAGE PROCESSING SYSTEMS
PROCESSING
COMMUNITY QUESTION ANSWERING
DATA-SOURCES
HEALTH EDUCATION
MEDICAL PROFESSIONALS
QUESTION-ANSWER PAIRS
URI: http://hdl.handle.net/10995/36860
SCOPUS ID: 84906774693
PURE ID: 365449
ISSN: 0302-9743
DOI: 10.1007/978-3-319-11382-1_2
metadata.dc.description.sponsorship: This work is partially supported by the Russian Foundation for Basic Research, project #14-07-00589 “Data Analysis and User Modelling in Narrow-Domain Social Media”. We also thank assessors who volunteered for the evaluation and Mail.Ru for granting us access to the data.
Appears in Collections:Научные публикации, проиндексированные в SCOPUS и WoS CC

Files in This Item:
File Description SizeFormat 
braslavski_clef2014.pdf238,6 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.