Trajectory Mining And Route Recommendation In Social Media

With the advance of various social media technology,especially the location acquisi-tion technology,social media based trajectory mining and route recommendation become more and more popular.However,the raw coordinate data captured by sensors often can-not reflect real positions.How to accurately match GPS trajectories to roads on a digital map is an important issue for many applications.Unfortunately,many existing methods still cannot meet stringent performance requirements in engineering.In particular,low sampling rate and lost data are usually big challenges.Personalized travel route recom-mendation aims to recommend personalized tourist attractions and generate routes.How to build interest model for users to find user's interest and understand user's real intention brings great challenges.In this work,we focus on map-matching of trajectory and per-sonalized route recommendation.As for map-matching,we propose a novel model using the related meta-information to describe a moving object,and present an algorithm called IF-Matching for map-matching.It can handle many ambiguous cases which cannot be correctly matched by existing methods.We run our algorithm with taxi trajectory data on a city-wide road network.Compared with two state-of-the-art algorithms of ST-Matching and the winner of GIS Cup 2012,our approach achieves more accurate results.As for personalized route recommendation,we leverage the Topical Package Model to describe user interests and route travel attributes.And the LSTM is used to enhance the user's input position.In the measurement space,top ranked routes are returned as the recom-mended results.The proposed method is evaluated on a real traveling dataset.Compared with two state-of-the-art methods,our method performs better for providing personalized travel routes.