ABSTRACT
A
location-aware news feed (LANF) system generates news feeds for a mobile user
based on her spatial preference (i.e., her current location and future
locations) and non-spatial preference (i.e., her interest). Existing LANF
systems simply send the most relevant geo-tagged messages to their users.
Unfortunately, the major limitation of such an existing approach is that, a
news feed may contain messages related to the same location (i.e.,
point-of-interest) or the same category of locations (e.g., food, entertainment
or sport). We argue that diversity is a very important feature for
location-aware news feeds because it helps users discover new places and
activities. In this paper, we propose D-MobiFeed; a new LANF system enables a
user to specify the minimum number of message categories (h) for the messages
in a news feed. In D-MobiFeed, our objective is to efficiently schedule news
feeds for a mobile user at her current and predicted locations, such that (i)
each news feed contains messages belonging to at least h different categories,
and (ii) their total relevance to the user is maximized. To achieve this
objective, we formulate the problem into two parts, namely, a decision problem
and an optimization problem. For the decision problem, we provide an exact solution
by modeling it as a maximum flow problem and proving its correctness. The
optimization problem is solved by our proposed three-stage heuristic algorithm.
We conduct a user study and experiments to evaluate the performance of
D-MobiFeed using a real data set crawled from Foursquare. Experimental results
show that our proposed three-stage heuristic scheduling algorithm outperforms
the brute-force optimal algorithm by at least an order of magnitude in terms of
running time and the relative error incurred by the heuristic algorithm is
below 1%. D-MobiFeed with the location prediction method effectively improves
the relevance, diversity, and efficiency of news feeds.
AIM
The
aim of this paper is is to efficiently schedule news feeds for a mobile user at
her current and predicted locations, such that (i) each news feed contains
messages belonging to at least h different categories, and (ii) their total
relevance to the user is maximized.
SCOPE
The
scope of this paper is to achieve this objective, we formulate the problem into
two parts, namely, a decision problem and an optimization problem.
EXISTING SYSTEM
MobiFeed
the state-of-the-art location-aware news feed system schedules news feeds for
mobile users. In MobiFeed, the relevance of a message m to Bob is measured by
both the content similarity between m and Bob’s submitted messages (i.e., a
non-spatial factor) and the distance between m and Bob (i.e., a spatial
factor). MobiFeed is motivated by the fact that, if the news feeds are only
computed based on a user’s location at the query time (i.e., it does not
consider the user’s future locations, e.g., GeoFeed), the total relevance of news
feeds is not optimized With the geographical distance between a message and a
mobile user in a relevance measure model, the relevance of a message to a
mobile user is changing as the user is moving. Such a dynamic environment gives
us an opportunity to employ location prediction technique to improve the quality
of news feeds and the system efficiency. Existing diversification problems
focus on retrieving an individual list of items with a certain level of
diversity. In contrast, with our location prediction techniques, we aim at
improving the quality of news feeds by scheduling multiple location- and
diversity-aware news feeds for mobile users simultaneously.
DISADVANTAGES
· A
news feed may contain messages related to the same location (i.e.,
point-of-interest) or the same category of locations (e.g., food, entertainment
or sport).
· In
MobiFeed considers a mobile environment that makes our location- and
diversity-aware news feed system unique and more challenging.
PROPOSED
SYSTEM
In
this project, propose D-MobiFeed; a new LANF system enables a user to specify
the minimum number of message categories (h) for the messages in a news feed.
In D-MobiFeed, our objective is to efficiently schedule news feeds for a mobile
user at her current and predicted locations, such that (i) each news feed
contains messages belonging to at least h different categories, and (ii) their
total relevance to the user is maximized. To achieve this objective, we
formulate the problem into two parts, namely, a decision problem and an
optimization problem. For the decision problem, we provide an exact solution by
modeling it as a maximum flow problem and proving its correctness. The
optimization problem is solved by our proposed three-stage heuristic algorithm.
We conduct a user study and experiments to evaluate the performance of
D-MobiFeed using a real data set crawled from Foursquare. Experimental results
show that our proposed three-stage heuristic scheduling algorithm outperforms
the brute-force optimal algorithm by at least an order of magnitude in terms of
running time and the relative error incurred by the heuristic algorithm is
below 1%. D-MobiFeed with the location prediction method effectively improves
the relevance, diversity, and efficiency of news feeds.
ADVANTAGES
· D-MobiFeed
with the location prediction method effectively improves the relevance,
diversity, and efficiency of news feeds.
· D-MobiFeed
can efficiently provide location- and diversity-aware news feeds when
maintaining their high quality in terms of relevance
SYSTEM CONFIGURATION
HARDWARE REQUIREMENTS:-
· Processor - Pentium –III
·
Speed - 1.1 Ghz
·
RAM - 256 MB(min)
·
Hard
Disk - 20 GB
·
Floppy
Drive - 1.44 MB
·
Key
Board - Standard Windows Keyboard
·
Mouse - Two or Three Button Mouse
·
Monitor -
SVGA
SOFTWARE REQUIREMENTS:-
·
Operating
System : Android OS
·
Front
End : JAVA
·
Database
: Sqlite
·
Tool :Eclipse
REFERENCES
Chow,
C.Xu, W. “A Location- and Diversity-aware News Feed System for Mobile Users”
IEEE Transactions ON Services Computing, Volume PP, Issue 99 MAY 2015.
