visual innovations for product search interfaces
DESCRIPTION
presentation @ 1st International Workshop on Future Search Engines at INFORMATIK 2014, September 22, 2014, Stuttgart (Germany) Keck, M., Herrmann, M., Henkens, D., Taranko, S., Nguyen, V., Funke, F., Schattenberg, S., Both, A., Groh, R.: Visual Innovations for Product Search Interfaces, 1st International Workshop on Future Search Engines at INFORMATIK 2014, 2014 http://visea-project.de/TRANSCRIPT
1st International Workshop on Future Search Engines - INFORMATIK 2014
Visual Innovations for Product Search InterfacesMON, 22 SEP 2014 - Stuttgart
Chair of Media Design
Technische Universität Dresden
This work has been supported by the European Union and the Free State Saxony through the European Regional Development Fund
Mandy Keck
Introduction
_ research project »VISEA - Visual Search Interfaces« _ focus: visual interfaces for product search _ use case: travel search + financial search
Problem: _ vague information need has to be transformed into a specific search query (Dörk et al. 2012)
Our Objective: _ supporting vague feelings and ideas in the process of information seeking
_ providing alternative visual approaches for product search besides the established keyword search paradigm
Fig. 01 TRAVEL SEARCH INTERFACE: WWW.OPODO.COM
Fig. 02 SEARCH INTERFACE FOR FINANCIAL PRODUCTS:
WWW.BOERSE-STUTTGART.DE
INFORMATIK 2014 - FoRESEE Workshop 22 Sep 2014 Visual Innovations for Product Search Interfaces 3 | 11
Motive-based Search
Motive: _ cause of search, specifies some general conditions _ influenced by emotions and interests of the user
NAVIGATIONALSEARCHING
TRANSACTIONALSEARCHING
INFORMATIONALSEARCHING
reaching a particular site performing a certain transaction acquisition of information
MOTIVE-BASED SEARCH
LOOKUP
EXPLORATORYSEARCH
known-item-search,fact-finding, verification
knowledge acquisition,discovery, comparison
vague information need (motive),aim: finding a suitable product
Fig. 03 MOTIVE-BASED SEARCH IN CONTEXT OF SEARCH ACTIVITIES (CF. MARCHIONINI 2006, WHITE 2009) AND WEB SEARCH INTENTION (CF. BRODER 2002, JANSEN 2008)
INFORMATIK 2014 - FoRESEE Workshop 22 Sep 2014 Visual Innovations for Product Search Interfaces 4 | 11
Search Paradigms
TUNKELANG 2006:
Direct Search _ allows users to simply write queries in a text box
Navigational Search _ provide guidance through the use of taxonomies
Clemmer & Davis 2011:
General to Specific _ use abstract criteria to progressively narrow down the result set to the desired set of answers
Specific to General _ starts with an example _ can be generalized to find similar results
GERNERAL TO SPECIFIC SPECIFIC TO GENERAL
NAV
IGAT
ION
AL S
EARC
HDI
RECT
SEA
RCH
FACETED SEARCH
FACETED BROWSINGFLICKR
GOOGLE IMAGESEARCH
LAST.FM
RETRIEVR
INFORMATIK 2014 - FoRESEE Workshop 22 Sep 2014 Visual Innovations for Product Search Interfaces 5 | 11
Visual Exploration System for Product Searches
Recommendation-based Search Approach: _ hides complex data strcuture of the search system _ leads to a small result set in a few steps
Analytical Approach: _ provides a deep insight into the data structure _ enables evaluation of the chosen product in comparison to the remaining information space
Seach by Example Approach: _ support users with little knowledge of the search domain _ goal: familiarizing with product features, finding of similar products
INFORMATIK 2014 - FoRESEE Workshop 22 Sep 2014 Visual Innovations for Product Search Interfaces 6 | 11
Recommendation-based Search Approach
‚getInspired‘ interface for travel search: triggers emotionally driven decisions
INFORMATIK 2014 - FoRESEE Workshop 22 Sep 2014 Visual Innovations for Product Search Interfaces 7 | 11
Analytical Approach based on Parallel Coordinates
analytical interface for multidimensional finanical data
INFORMATIK 2014 - FoRESEE Workshop 22 Sep 2014 Visual Innovations for Product Search Interfaces 8 | 11
Analytical Approach based on Parallel Sets
analytical interface for travel search
INFORMATIK 2014 - FoRESEE Workshop 22 Sep 2014 Visual Innovations for Product Search Interfaces 9 | 11
Search by Example Approach
Prod
uktg
rupp
eBa
sisw
ert
Zins
Rohstoff
Währung
Aktie
Wert
Index
Volatilität
Bonus-ZertifikatDeutsche Post AG12/2014 (SG42OT)
BONUS-ZERTIFIKAT - DEUTSCHE BANK AG 12 /2014 (SG21Q6)
PERFORMANCE 1 JAHR: -6.59%PERFORMANCE 6 MONATE: +3.23%PERFORMANCE 1 MONAT: -2.90%PERFORMANCE 1 WOCHE: +4.98%
PRODUKTTYP:
PRODUKTGRUPPE: BONUSZERTIFIKAT
Bonus-Zerti�kate haben eine feste Laufzeit. Weiter wird ein Bonuszerti�kat durch zwei Param-eter bestimmt, die Barriere, auch Sicherheitslevel genannt, und das Bonuslevel. Abhängig von der Wahl dieser Parameter reagiert der Wert des Zerti�kates auf die Entwicklung seines Ba-siswertes.
Das Sicherheitslevel spielt eine wesentliche Rolle: Berührt oder durchbricht der Basiswert die Barriere während der Laufzeit auch nur ein einziges Mal, dann ändert sich der Charakter des Bonuszerti�kats vollständig: Es wird zu einem normalen Trackerzerti�kat und der Bonus ist un-widerru�ich verloren, auch wenn am Fälligkeitstag der Basiswert wieder über der Barriere liegt. Allerdings unterscheidet sich die Rendite eines Bonuszerti�kates von der eines Trackerzerti�-kates, da der Preis des Bonuszerti�kates um den Wert der Barrieroption über dem Preis eines entsprechenden Trackerzerti�kates liegt.
BASISWERT: INDEX LAUFZEIT:
BEWERTUNGSTAG: 19.12.2014
AUSGABETAG: 12.04.2012 WERT:
BRIEF: 47.45
GELD: 47.35 SPREAD: 0.21%
visual approach for similarity search in a financial product search scenario
INFORMATIK 2014 - FoRESEE Workshop 22 Sep 2014 Visual Innovations for Product Search Interfaces 10 | 11
Conclusion & Future Work
_ search experience and speed in product search scenarios can be significantly improved by visually appealing interfaces
_ recommendation-based approach: good results in short time
_ analytical approach: better results, but requires more effort and time
challenges: _ management of a huge variety of different informati-on sources and formats
_ good balance between insights in the underlying data sources and a user-friendly, easily comprehensible interface
GERNERAL TO SPECIFIC SPECIFIC TO GENERAL
NAV
IGAT
ION
AL S
EARC
HDI
RECT
SEA
RCH
PARALLEL COORDINATES
GET-INSPIRED
PARALLEL SETS
SEARCH BYEXAMPLE
INFORMATIK 2014 - FoRESEE Workshop 22 Sep 2014 Visual Innovations for Product Search Interfaces 11 | 11
References
Dörk, M.; Williamson, C. and Carpendale, S.: Navigating tomorrow’s web: From searching and browsing to visual exploration. ACM Trans. Web 6, 3, Article 13, 28 pages. New York, USA (2012)
Broder, A.: A taxonomy of Web search. SIGIR Forum, 36(2), 3–10., 2002
Jansen, B. J., Booth, D. L., Spink, A.: Determining the informational, navigational, and transactional intent of Web queries. Inf. Process. Manage. 44, 1251-1266., 2008
Marchionini, G.: Exploratory search: from finding to understanding. Communications of the ACM. New York, USA: ACM, 41-46, 2006
White, R. W., Roth, R. A.: Exploratory Search: Beyond the Query-Response Paradigm. San Rafael, California: Morgan and Claypool Publishers, 2009
Tunkelang, D.: Dynamic category sets: An approach for faceted search. ACM SIGIR, 6, 2006
Clemmer, A. & Davis, S. Smeagol: A “Specific-to-General” Semantic Web Query Interface Paradigm for Novices.volume 6860 of Lec-ture Notes in Computer Science, pages 288-302, Springer Heidelberg Verlag, 2011