Author : Miss.Vanita M.Gaikwad 1
Date of Publication :10th April 2017
Abstract: A location-aware news feed (LANF) system generates news feeds for a mobile user supported their abstraction preference (i.e., their current location and future locations) and non-spatial preference (i.e., their interest). Existing LANF systems merely send the foremost relevant geo-tagged messages to their users. unfortunately, the key limitation of such associate existing approach is that, a news feed might contain messages related to identical location (i.e., point-of-interest) or identical class of locations (e.g., food, diversion or sport). We argue that diversity may be an important feature for location-aware news feeds as a result of it helps users discover new places and activities. In this paper, we propose News-Feed; a replacement LANF system allows a user to specify the minimum variety of message classes (h) for the messages in a very news feed. In News-Feed, our objective is to with efficiency schedule news feeds for a mobile user at their current and expected locations, such (i) every news feed contains messages happiness to a minimum of h completely different classes, and (ii) their total connectedness to the user is maximized. To attain this objective, we formulate the matter into 2 components, namely, a choice drawback and an improvement drawback. For the choice drawback, we offer a definite answer by modeling it as a most flow drawback and proving its correctness. The improvement drawback is resolved by our projected three-stage heuristic formula. we conduct a user study and experiments to estimating the performance of News-Feed employing a real information set crawled from Experimental results show that our projected three-stage heuristic planning formula outperforms the brute-force optimum formula by a minimum of associate order of magnitude in terms of period of time and also the relative error incurred by the heuristic formula is below 125th. News-Feed with the placement prediction methodology effectively improves the connectedness, diversity, and potency of reports feeds.
Reference :
-
- 2010CensusTIGER/Line Shapefiles. http:// www.census.gov/ geo/ www/ tiger/ tgrshp2010/ tgrshp2010.html.
- Z. Abbassi, V. S. Mirrokni, and. Thakur. Diversity maximization under matroid constraints. In ACM KDD, 2013.
- G. Adomavicius and Y. Kwon. Improving aggregate recommendation diversity using ranking-based techniques. IEEE TKDE, 24(5):896–911, 2012.
- G. Adomavicius and A. Tuzhilin. Toward the next generation of recommender Systems: A survey of the state-of-the-art and possible extensions. IEEE TKDE, 17(6):734–749, 2005.
- R. Agrawal, S. Gollapudi, A. Halverson, and S. Leong. Diversifying search results. In ACM WSDM, 2009.
- R. K. Ahuja, T. L. Magnanti, and J. B. Orlin. Network Flows: Theory, Algorithms, and Applications. Prentice Hall, 1993.
- J. Bao, M. F. Mokbel, and C.-Y. Chow. GeoFeed: Location-aware news feed system. In IEEE ICDE, 2012
- J. Carbonell and J. Goldstein. The use of mmr, diversity-based reranking for reordering documents and producing summaries. In ACM SIGIR, 1998.
- H. Jeung, M. L. Yiu, X. Zhou, and C. S. Jensen. Path prediction and predictive range querying in road network databases.19 (4):585–602, 2010
- lpsolve 5.5.5.0. http:// lpsolve.sourceforge.net /5.5/.
- A. Machanavajjhala, D. Kifer, J. Gehrke, and M.Venkitasubramaniam. ldiversity: Privacy beyondkanonymity.ACM TKDD, 1(1):3, 2007.
- C. D. Manning, P. Raghavan, and H. Sch ̈utze.Introduction to InformationRetrieval. Cambridge University Press, 2008.
- Privacybeyondkanonymity.ACM TKDD, 1(1):3, 2007.
- A. Silberstein, J. Terrace, B. F. Cooper, and R. Ramakrishnan. Feeding Frenzy: Selectively materializing user‘s event feed. In ACM SIGMOD, 2010.
- C. X. Zhai,W.W. Cohen, and J. Lafferty. Beyond independent relevance: Methods and evaluation metrics for subtopic retrieval. In ACM SIGIR, 2003.