Location based video navigation using task extracted from the web

Article type: Research Article

Authors: Fukazawa, Yusuke^{a; *} | Ota, Jun^b

Affiliations: [a] NTT DOCOMO, Inc. 3-6 Hikari-no-oka, Yokosuka, Kanagawa, Japan | [b] The University of Tokyo, Kashiwanoha, Kashiwa, Chiba, Japan

Correspondence: [*] Corresponding author: Yusuke Fukazawa, NTT DOCOMO, Inc. 3–6 Hikari-no-oka, Yokosuka, Kanagawa, Japan. E-mail: fukazawayuu@nttdocomo.co.jp

Abstract: In this paper, we propose an application called TaskGuideRoid(TGR). TGR recommends YouTube contents with task-based descriptions. To collect the task description with both high coverage and precision, we mine tasks from the web given the input of lexico-syntactic pattern using sightseeing spot names. A user evaluation shows that TGR improved the frequency of watching videos by about 15%. From the results of an interview, 90.0% of the subjects gave TGR high marks in terms of finding new enjoyable videos. Furthermore, We show that TGR allows users to find sightseeing spots through task based descriptions at unknown places.

Keywords: Location based services, video recommendation, web mining

DOI: 10.3233/KES-130284

Journal: International Journal of Knowledge-based and Intelligent Engineering Systems, vol. 18, no. 1, pp. 43-54, 2014