Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Search intention analysis for task- and user-centered visualization in big data applications

 
: Burkhardt, Dirk; Pattan, Sachin; Nazemi, Kawa; Kuijper, Arjan

:
Volltext (PDF; )

Procedia computer science 104 (2017), S.539-547
ISSN: 1877-0509
International Conference on Tissue Engineering (ICTE) <2016, Riga>
Englisch
Zeitschriftenaufsatz, Konferenzbeitrag, Elektronische Publikation
Fraunhofer IGD ()
Human-computer interaction (HCI); information retrieval; user-centered design; predictions; Guiding Theme: Digitized Work; Research Area: Human computer interaction (HCI)

Abstract
A new approach for classifying users' search intentions is described in this paper. The approach uses the parameters: word frequency, query length and entity matching for distinguishing the user's query into exploratory, targeted and analysis search. The approach focuses mainly on word frequency analysis, where different sources for word frequency data are considered such as the Wortschatz frequency service by the University of Leipzig and the Microsoft Ngram service (now part of the Microsoft Cognitive Services). The model is evaluated with the help of a survey tool and few machine learning techniques. The survey was conducted with more than one hundred users and on evaluating the model with the collected data, the results are satisfactory. In big data applications the search intention analysis can be used to identify the purpose of a performed search, to provide an optimal initially set of visualizations that respects the intended task of the user to work with the result data.

: http://publica.fraunhofer.de/dokumente/N-435470.html