Enabling maps/location searches on mobile devices: constructing a POI database via focused crawling and information extraction

ABSTRACT

With the popularity of mobile devices and smartphones, we have witnessed rapid growth in mobile applications and services, especially in location-based services (LBS). According to a mobile marketing survey, maps/location searches are among the most utilized services on smartphones. Points of interest (POIs), such as stores, shops, gas stations, parking lots, and bus stops, are particularly important for maps/location searches. Existing map services such as Google Maps and Wikimapia are constructed manually either professionally or with crowd sourcing. However, manual annotation is costly and limited in current POI search services. With the abundance of information on the Web, many store POIs can be extracted from the Web. In this paper, we focus on automatically constructing a POI database to enable store POI map searches. We propose techniques that are required to construct a POI database, including focused crawling, information extraction, and information retrieval techniques. We first crawl Yellow Page web sites to obtain vocabularies of store names. These vocabularies are then investigated with search engines to obtain sentences containing these store names from search snippets in order to train a store name recognition model. To extract POIs scattered across the Web, we propose a query-based crawler to find address-bearing pages that might be used to extract addresses and store names. We crawled 1.25 million distinct POI pairs scattered across the Web and implemented a POI search service via Apache Lucent’s search platform, called Solr. The experimental results demonstrate that the proposed geographical information retrieval model outperforms Wikimapia and a commercial app called ‘What’s the Number?’

KEYWORDS:

• Location-based service
• POI crawling
• store name recognition
• POI relation pairing
• geographic information retrieval

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes

1. Mobile marketing statistics, http://www.smartinsights.com/mobile-marketing/mobile-marketing-analytics/ mobile-marketing- statistics/

2. OpenStreetMap, http://www.openstreetmap.org

3. Wikimapia, http://wikimapia.org/

4. Solr, http://lucene.apache.org/solr/

5. What’s The Number, https://play.google.com/store/apps/details?id=com.StorySense.WhatsTheNumberLite& hl = en

6. 疾疾店家現身, https://play.google.com/store/apps/details?id=com.widmlab.powerpoi&hl=zh_TW

7. PowerPOI project, https://sites.google.com/site/nculab/project/powerpoi

8. GATE, http://en.wikipedia.org/wiki/General_Architecture_for_Text_Engineering

9. OpenNLP, http://en.wikipedia.org/wiki/OpenNLP

10. Stanford CoreNLP, http://en.wikipedia.org/wiki/Stanford_CoreNLP

11. https://foursquare.com/

12. https://developers.facebook.com/docs/reference/api/search/

13. https://developers.google.com/places/

14. http://www.ipeen.com.tw/service/service_teach.php

15. http://www.w3.org/WAI/intro/wcag

16. Commerce Industrial Service: http://gcis.nat.gov.tw/main/indexC.jsp

17. http://gcis.nat.gov.tw/

18. http://www.post.gov.tw

19. CRF++: Yet Another CRF toolkit, http://taku910.github.io/crfpp/

20. Open data from the Ministry of Transportation and Communications was downloaded in October, 2014, http://gist-map.motc.gov.tw/

21. http://lucene.apache.org/

Additional information

Funding

This work was partially supported by the Ministry of Science and Technology, Taiwan under [grant number MOST103-2221-E-008-094].