DOI QR코드

DOI QR Code

Location Recommendation System based on LBSNS

LBSNS 기반 장소 추천 시스템

  • Jung, Ku-Imm (Department of Strategy Marketing, SeeOn Inc.) ;
  • Ahn, Byung-Ik (Department of Strategy Marketing, SeeOn Inc.) ;
  • Kim, Jeong-Joon (Division of Computer Science & Engineering, Konkuk University) ;
  • Han, Ki-Joon (Division of Computer Science & Engineering, Konkuk University)
  • Received : 2014.04.04
  • Accepted : 2014.06.20
  • Published : 2014.06.28

Abstract

In LBSNS(Location-based Social Network Service), users can share locations and communicate with others by using check-in data. The check-in data consists of POI name, category, coordinate and address of locations, nickname of users, evaluating grade of locations, related article/photo/video, and etc. If you analyze the check-in data from the location-based social network service in accordance with your situation, you can provide various customized services. Therefore, In this paper, we develop a location recommendation system based on LBSNS that can utilize the check-in data efficiently. This system analyzes the location category of the check-in data, determines the weighted value of it, and finds out the similarity between users by using the Pearson correlation coefficient. Also, it obtains the preference score of recommended locations by using the collaborated filtering algorithm and then, finds out the distance score by applying the Euclidean's algorithm to the recommended locations and the current users' locations. Finally, it recommends appropriate locations by applying the weighted value to the preference score and the distance score. In addition, this paper approved excellence of the proposed system throughout the experiment using real data.

위치 기반 소셜 네트워크 서비스에서 사용자들은 체크인 데이터를 이용해 장소를 공유하고 커뮤니케이션을 한다. 체크인 데이터는 POI명, 카테고리, 장소 좌표/주소, 사용자 닉네임, 장소 평가 점수, 관련 글/사진/동영상 등으로 구성된다. 위치 기반 소셜 네트워크 서비스에서 이러한 체크인 데이터를 상황에 맞게 분석하면 다양한 맞춤형 서비스를 제공할 수 있다. 따라서, 본 논문에서는 사용자 체크인 데이터를 활용할 수 있는 LBSNS(Location-based Social Network Service) 기반 장소 추천 시스템을 개발하였다. LBSNS 기반 장소 추천 시스템은 체크인 데이터 중 장소 카테고리를 분석하여 가중치를 추출하고, 피어슨 상관계수를 이용해 사용자간의 유사도를 구한다. 그리고 협업적 필터링 알고리즘을 이용하여 추천 장소에 대한 선호도 점수를 구하고, 추천 대상 장소의 위치와 사용자의 현재 위치에 대해 유클라디안 알고리즘을 적용하여 거리 점수를 구한다. 마지막으로, 선호도 점수와 거리 점수에 대해 가중치 계수를 적용하여 상황에 맞게 장소를 추천한다. 또한, 본 논문에서는 실제 데이터를 이용한 실험을 통해 본 논문에서 제시한 시스템의 우수성도 입증하였다.

Keywords

References

  1. H. Y. Kim and J. H. Oh, The Current state and social meaning of domestic and foreign SNS. Hongik University, 2012.
  2. J. M. Ryu, C. P. Hong, K. B. Kang, D. H. Kang, D. Y. Yangand J. W. Jwa, Development of mobile context awareness restaurant recommendation services. The Korea Contents Association, Vol. 7, No. 5, pp. 138-145, 2007. https://doi.org/10.5392/JKCA.2007.7.5.138
  3. B. I. Ahn, Location-based services of the mobile service. KT Economic Research, Trend Report, 2011.
  4. eMarketer, Social Network Ad Revenues Worldwide. Market Trend Report, 2012.
  5. J. Y. Oh, Comparison analysis of Korean, American and Japanese's SNS Service. National Information Society Agency, IT Policy Research Series, Vol. 11, 2009.
  6. S. Y. Kim, Pronoun of LBS the change of Foursquare. KT Economic Research, Trend Report, 2012.
  7. S. B. Cha, An analysis of Structural equation models on university students' Social Network Service participation and learning outcomes. Konkuk University, 2011.
  8. H. C. Shin, A location-based collaborative filtering recommender using quadtree. Yonsei University, 2011.
  9. S. H. Lee, B. K. Kim, T. B. Yoon and J. H. Lee, The method for extraction of meaningful places based on behavior Information of user, Korean Institute of Intelligent Systems, Vol. 20, No. 4, pp. 503-508, 2010. https://doi.org/10.5391/JKIIS.2010.20.4.503
  10. S. J. Bae, Study of personalized recommendation algorithms for new books on internet bookstores. Chungnam University, 2003.