Extracting Professional Preferences of Users from Natural Language Essays

Toprak, Cigdem; Müller, Christof; Gurevych, Iryna

Veröffentlicht

Extracting Professional Preferences of Users from Natural Language Essays

Toprak, Cigdem; Müller, Christof ; Gurevych, Iryna

This paper presents an unsupervised sentiment analysis approach for extracting professional preferences of users from natural language essays in a career recommendation scenario. Our system first extracts terms facilitating career recommendation such as objects, activities, hobbies, and places from the essays. Then, it applies a lexicon-based sentiment analysis approach to assign polarities representing user preferences.

Vorschau

Einordnung

Konferenz:: GSCL-SYMPOSIUM »Sprachtechnologie und eHumanities«, 26.02.2009 - 27.02.2009, Universität Duisburg-Essen, Campus Duisburg
Erschienen in:: GSCL-Symposium "Sprachtechnologie und eHumanities"
(16.01.2015), S. 103-110
Datum der Veröffentlichung:: 16.01.2015
URN:: urn:nbn:de:hbz:464-20150116-151107-4
Sprache:: Englisch
Ressourcentyp:: Text
Schlagwörter:: unsupervised sentiment analysis; information extraction
Kollektion:: E-Publikationen
Dewey Dezimal-Klassifikation:: 000 Informatik, Wissen, Systeme
Sachgruppen der Deutschen Nationalbibliographie:: 400 Sprache, Linguistik
Sachgruppen der Deutschen Nationalbibliographie:: 004 Informatik
Einrichtung:: Externe, Sonstige Einrichtungen
Förderung:: This work was supported by the German Research Foundation (DFG) under the grant GU 798/1-2, Semantic Information Retrieval from Texts in the Example Domain Electronic Career Guidance, and by the Volkswagen Foundation as part of the Lichtenberg-Professorship Program under grant No. I/82806.
Datum:: 2009-02-14