دانلود رایگان مقاله لاتین آنالیز سیستم توصیه برای شبکه اجتماعی مبتنی بر مکان از سایت الزویر


عنوان فارسی مقاله:

مطالعه و تجزیه و تحلیل سیستم های توصیه برای شبکه اجتماعی مبتنی بر مکان (LBSN) با کلان داده ها


عنوان انگلیسی مقاله:

A study and analysis of recommendation systems for location-based social network (LBSN) with big data



برای دانلود رایگان مقاله آنالیز سیستم توصیه برای شبکه اجتماعی مبتنی بر مکان  اینجا کلیک نمایید.





مقدمه انگلیسی مقاله:

1. Introduction

Recommender systems or recommendation systems (RS) collect information based on the preferences of users (for example—songs, movies, jokes, books, travel destination and e-learning material). Recommender systems work based on users’ information from different sources and provide recommendation of items. This information can be explicit (user rating) and implicit (monitoring user’s behaviour), with millions of users using social networking services like Facebook, Twitter, and so forth. The rich knowledge that has accumulated in these social networking sites enables a variety of recommendation systems for its users. A social network is an abstract structure comprised of individuals connected by one or more types of relations, such as friendship, shared knowledge, and common interests as stated by Zheng, Zhang, Xie, and Ma (2009). Location data add strength to the connection of the social networks. A location can be represented in relative, absolute, and symbolic form. Location is usually represented in three kinds of geographical representations—a point location, a region, and a trajectory. In recent times, localisation techniques have enhanced social networking services, allowing the users to share their location-related content, and locations such as geo-tagged photos and notes. This is known as location-based social networks (LBSNs) (Zheng et al., 2009). An LBSN adds a location to an existing social network, and also tells the people in their social network that they can share their location-related information. Based on the location-related information, a new abstract structure is derived and connects connected individuals based on their location-related content, such as photos, texts and videos. Instant location and the history of a person are given as a timestamp during a certain period. The advances in wireless communication technologies and location acquisition enables people to add a location dimension to traditional social networks and promotes a bunch of LBSN services, such as Foursquare, GeoLife and Loopt, where users can easily share their experiences in the physical world through mobile devices. The location dimension bridges the gap between the physical world and the digital online social networking services, giving rise to new opportunities and challenges in traditional recommender systems in the following aspects—complex objects and relations, and rich knowledge. Location is one of the important components of user context and implies extensive knowledge about a user’s interests and behaviour, thereby providing us with opportunities to better understand users in an abstract structure not only according to user behaviour, but the mobility of the user and his/her activities in the physical world. In recent times location-based services, such as tour guide and locationbased social network, have accumulated a lot of location data. Today, the positioning function in mobile devices, such as GPSphones, lets people know their locations easily. This location data provide various location-based services on the web and has shown itself to be attractive to the users. In real time, data are huge in volume, but data warehouses use smallscale datasets of users for recommendation. When it comes to real-time scenario, these techniques may fail because millions of users will use social networks at the same time. The major challenges to be addressed in LBSN recommendation are 1) location-context awareness; 2) heterogeneous domain and 3) rate of growth. Different types of data sources are used in recommendation systems for LBSNs, including 1) user profiles, 2) user online histories and 3) user location histories. This involves huge volumes of data in real-time scenario. Most recommendation systems in LBSNs currently use only one type of data source to make recommendations. Moreover, many of the data sources are related and may mutually reinforce each other. By considering more diversified data sources, more effective recommendations can be provided. For instance, the user online interactions, social structures and location histories are all very relevant to friend recommendation. If two users have more online interactions, are close in the social structure, and have overlapped location histories, these users are likely to be compatible. A friend recommender system that can consider all these factors will make higher quality friend recommendations. We carried out an analysis, based on the characteristics of a recommender system, to give a comparison between big data and data warehouse with a dataset collected from Foursquare users, using a qualitative approach. This paper is organised as follows: Section 2 deals with literature review; Section 3 explains the challenges of the domain; Section 4 provides the objective of the paper; Section 5 details the dataset discussed in this paper; Section 6 gives characteristics of a location-based recommendation system; Section 7 explains the qualities of the location-based recommendation system, and Section 8 provides the conclusion.



برای دانلود رایگان مقاله آنالیز سیستم توصیه برای شبکه اجتماعی مبتنی بر مکان اینجا کلیک نمایید.






کلمات کلیدی:

Recommendations in location-based social networks: A survey (PDF ... https://www.researchgate.net/.../272389361_Recommendations_in_location-based_socia... We propose three taxonomies that partition the recommender systems .... “A location-based social network (LBSN) does not only mean adding a location to. Recommendations in Location-based Social Networks: A Survey ... https://www.microsoft.com/.../recommendations-in-location-based-social-networks-a-s... Nov 1, 2014 - We refer to these social networks as location-based social networks ... We present a comprehensive survey of recommender systems for ... Images for recommendation systems for location ... Image result for recommendation systems for location-based social network (LBSN) Image result for recommendation systems for location-based social network (LBSN) Image result for recommendation systems for location-based social network (LBSN) Image result for recommendation systems for location-based social network (LBSN) Image result for recommendation systems for location-based social network (LBSN) Image result for recommendation systems for location-based social network (LBSN) More images for recommendation systems for location-based social network (LBSN) Report images [PDF]Location-based and Preference-Aware Recommendation Using ... dmlab.cs.umn.edu/new/papers/gis12b.pdf by J Bao - ‎2012 - ‎Cited by 328 - ‎Related articles The popularity of location-based social networks provide us with a new platform to .... of physical locations) in a LBSN, our recommender system can fa-. [PDF]Recommendation in location-based and event-based social networks web.tuke.sk/fei-cit/wikt2015/zbornik/52.pdf system (GPS), location-based social networks (LBSN) have attracted millions ... (POI) recommendation system play an important role in LBNS since it can help. Searches related to recommendation systems for location-based social network (LBSN) location based recommendation system exploiting geographical influence for collaborative point-of-interest recommendation location recommendation