Eylem Seç
Point-of-interest Recommendation in Location-based Social Networks
Başlık:
Point-of-interest Recommendation in Location-based Social Networks
Yazar:
Zhao, Shenglin, author.
ISBN:
9780438147997
Yazar Ek Girişi:
Fiziksel Tanımlama:
1 electronic resource (184 pages)
Genel Not:
Source: Dissertation Abstracts International, Volume: 79-11(E), Section: B.
Advisors: Rung Tsong Michael Lyu; Kuo Chin Irwin King.
Özet:
Location-based social networks (LBSNs) have become popular recently because of the explosive increase of smart phones that makes users easily to access to the LBSN Apps. More than 2.3 billion people worldwide use smart phones in 2017 predicted by EMarketer, which prospers the online LBSNs. A typical LBSN such as Foursquare collects users' check-in information including visited locations' geographical information (latitude and longitude) and users' comments at the location and allows users to make friends and share information as well. Driven by the collected big data in LBSNs, point-of-interest (POI) recommendation arises to improve the user experience in the App, which attempts to suggest each user a list of POIs that the user may feel interesting and be willing to visit in the future.
Developing POI recommendation systems requires analytics of the human mobility with respect to real-world POIs. Different from watching on Netflix or shopping on Amazon, checking-in at a POI in LBSNs is a physical activity, which causes the most important feature in POI recommendation: geographical influence. In addition, check-ins exhibit specific temporal characteristics. For instance, users check-in at POIs around the office in the day time while at bars in the evening. These geographical and temporal features make the POI recommendation more challenging than traditional recommendation systems.
In this thesis, we systematically study the problem of POI recommendation in LBSNs. In particular, we review the literature in the area of POI recommendation, analyze the user mobility in LBSNs, and develop POI recommendation systems. First, we review state-of-the-art POI recommendation techniques and discover the challenges in POI recommendation systems. Second, we analyze the user mobility in LBSNs from geographical and temporal perspective respectively and show how to capture the geographical and temporal influence in a POI recommendation system. Third, we develop two POI recommendation systems: Geo-Teaser and STELLAR. Finally, we conclude this thesis and point out future work directions.
Notlar:
School code: 1307
Tüzel Kişi Ek Girişi:
Mevcut:*
Yer Numarası | Demirbaş Numarası | Shelf Location | Lokasyon / Statüsü / İade Tarihi |
---|---|---|---|
XX(697045.1) | 697045-1001 | Proquest E-Tez Koleksiyonu | Arıyor... |
On Order
Liste seç
Bunu varsayılan liste yap.
Öğeler başarıyla eklendi
Öğeler eklenirken hata oldu. Lütfen tekrar deneyiniz.
:
Select An Item
Data usage warning: You will receive one text message for each title you selected.
Standard text messaging rates apply.