Market Intelligence: Linked Data-driven Entity Resolution for Customer and Competitor Analysis
Abstract:
In this paper, we present a linked data-driven method for named entity recognition and disambiguation which is applied within an industry customer and competitor analysis application. The proposed algorithm primarily targets the domain of geoparsing and geocoding, but it can easily be adapted to other problems such duplicate detection. The contributions of this paper are three fold: First, we want to give an overview of Market Intelligence, a customer and competitor analysis application developed for Siemens Energy, which allows users to pose questions and queries on regularly crawled websites, emails and RSS feeds, to detect and respond to competitor, customer, and market trends more effectively. Second, we describe the UIMA-based processing architecture that builds the framework for analyzing and converting unstructured heterogeneous documents into a structured and semantically-enhanced knowledge representation. Third, we propose a novel algorithm that is used within the framework for content analysis and entity disambiguation. The performed evaluation shows with an accuracy of up to 91.69% that the proposed method for named entity recognition and disambiguation is very effective, while at the same time relying on Linked Data only.
Title: Market Intelligence: Linked Data-driven Entity Resolution for Customer and Competitor Analysis
Authors: Ulli Waltinger, Dan Tecuci, Florin Picioroaga, Cosmin Grigoras, Sean Sullivan
Pub/Conf: Web Engineering Lecture Notes in Computer Science Volume, 7977, 2013, pp 467-481
BibTeX:
@inproceedings{DBLP:conf/icwe/WaltingerTPGS13,
author = {Ulli Waltinger and
Dan Tecuci and
Florin Picioroaga and
Cosmin Grigoras and
Sean Sullivan},
title = {Market Intelligence: Linked Data-driven Entity Resolution
for Customer and Competitor Analysis},
booktitle = {Web Engineering - 13th International Conference, ICWE 2013,
Aalborg, Denmark, July 8-12, 2013.},
editor = {Florian Daniel and
Peter Dolog and
Qing Li},
year = {2013},
pages = {467-481},
}
