Applications of Machine Learning to Location-based Social Networks
1 like846 views
This document summarizes an application of machine learning techniques to location-based social networks. It discusses two applications: 1) GeoSRS, a hybrid social recommender system that provides personalized venue recommendations to users. It extracts data from Foursquare using an API, performs text modeling on tip content, and generates recommendations using both collaborative and content-based approaches. 2) Tweet-SCAN, an event discovery technique that identifies dense groups of geolocated tweets close in space, time, and topic to discover real-world events. It extends the DBSCAN clustering algorithm and represents tweet topics using probabilistic models. The technique is evaluated on tweets from Barcelona events.
![18
Research lines
Understanding users
– User similarity/link prediction
– Experts/influencers detection
– Community discovery
Understanding locations
– Generic recommendation
• Most interesting locations and travel routes
• Itinerary planning
• Location-activity recommenders
– Personalized recommendation: GeoSRS [Capdevila et al. 2015]
Understanding events
– Anomaly detection: Tweet-SCAN [Capdevila et al. 2015]
– Crowd behavioral patterns
Zheng, Y. 2011](https://image.slidesharecdn.com/appiatosn-151126100313-lva1-app6891/85/Applications-of-Machine-Learning-to-Location-based-Social-Networks-18-320.jpg)
![19
Research lines
Understanding users
– User similarity/link prediction
– Experts/influencers detection
– Community discovery
Understanding Locations
– Generic recommendation
• Most interesting locations and travel routes
• Itinerary planning
• Location-activity recommenders
– Personalized recommendation: GeoSRS [Capdevila et al. 2015]
Understanding events
– Anomaly detection: Tweet-SCAN [Capdevila et al. 2015]
– Crowd behavioral patterns
Zheng, Y. 2011](https://image.slidesharecdn.com/appiatosn-151126100313-lva1-app6891/85/Applications-of-Machine-Learning-to-Location-based-Social-Networks-19-320.jpg)
![20
Research lines
Understanding users
– User similarity/link prediction
– Experts/influencers detection
– Community discovery
Understanding locations
– Generic recommendation
• Most interesting locations and travel routes
• Itinerary planning
• Location-activity recommenders
– Personalized recommendation: GeoSRS [Capdevila et al. 2015]
Understanding events
– Anomaly detection: Tweet-SCAN [Capdevila et al. 2015]
– Crowd behavioral patterns
Zheng, Y. 2011](https://image.slidesharecdn.com/appiatosn-151126100313-lva1-app6891/85/Applications-of-Machine-Learning-to-Location-based-Social-Networks-20-320.jpg)
![60
Probabilistic topic modeling
VAN VAN MARKET - 🚐🚎🍤🍱🍜 Mercat gastronòmada #lepetitbangkok @ Parc de la Ciutadella
http://t.co/5CvnUFoIDa
Topic Proportions: [(1, 0.30002802458675537), (11,0.58330530874655417)]](https://image.slidesharecdn.com/appiatosn-151126100313-lva1-app6891/85/Applications-of-Machine-Learning-to-Location-based-Social-Networks-60-320.jpg)
Applications of Machine Learning to Location-based Social Networks
- 1. Applications of Machine Learning to Location-based Social Networks Joan Capdevila Pujol e-mail: jc@ac.upc.edu website: http://people.ac.upc.edu/jc Advisors: Jordi Torres Viñals, Jesús Cerquides Bueno
- 2. 2 Table of contents Motivation Location-based Social Networks (LBSNs) App 1: GeoSRS: A social recommender system App 2: Tweet-SCAN: An event discovery technique Conclusions and future trends
- 3. MOTIVATION 3
- 5. 5 AS A “HOT OR NOT” GAME
- 6. 6
- 7. 7 A ML geek might have thought: “With all this tagged data, I am going to build a classifier to decide whether the person in the pic is hot or not.”
- 8. 8 Mark Zuckerberg probably thought: “I’d rather prefer to keep playing to scale up the network and then…”
- 11. 11 User engagement through several social networking services: Linking to friends, colleagues, etc. Setting school/college Tagging friends to pictures Liking publications Geolocating content Reviewing business Expressing how one feels …
- 12. 12 User engagement through several social networking services: Linking to friends, colleagues, etc. à Social graphs Setting school/college à User profiles Tagging friends to pictures à Tagged images Liking publications à Rating information Geolocating content à Geolocated content Reviewing business à Textual comments Expressing how one feels à People feelings …
- 13. 13 Community detection Content-based Recommender Sentiment Analysis Image recognitionTopic Modeling
- 15. Social Networks (SNs) VIRTUALWORLD 2004 - 2010
- 16. Location-based Social Networks (LBSNs) VIRTUALWORLD Mobile communication + Positioning technologies PHYSICALWORLD 2010 - …
- 17. 17 Locations Location-acquisition technologies – Outdoor: GPS, GSM, etc. – Indoor: Wi-Fi, RFID, etc. Representation of locations – Absolute (e.g. latitude-longitude coordinates) – Symbolic (e.g. at Pl. Catalunya, at Aeroport Girona-Costa Brava ) Forms of locations – Point locations (e.g. Foursquare venues) – Regions (e.g. Twitter places) – Trajectories (e.g. Strava)
- 18. 18 Research lines Understanding users – User similarity/link prediction – Experts/influencers detection – Community discovery Understanding locations – Generic recommendation • Most interesting locations and travel routes • Itinerary planning • Location-activity recommenders – Personalized recommendation: GeoSRS [Capdevila et al. 2015] Understanding events – Anomaly detection: Tweet-SCAN [Capdevila et al. 2015] – Crowd behavioral patterns Zheng, Y. 2011
- 19. 19 Research lines Understanding users – User similarity/link prediction – Experts/influencers detection – Community discovery Understanding Locations – Generic recommendation • Most interesting locations and travel routes • Itinerary planning • Location-activity recommenders – Personalized recommendation: GeoSRS [Capdevila et al. 2015] Understanding events – Anomaly detection: Tweet-SCAN [Capdevila et al. 2015] – Crowd behavioral patterns Zheng, Y. 2011
- 20. 20 Research lines Understanding users – User similarity/link prediction – Experts/influencers detection – Community discovery Understanding locations – Generic recommendation • Most interesting locations and travel routes • Itinerary planning • Location-activity recommenders – Personalized recommendation: GeoSRS [Capdevila et al. 2015] Understanding events – Anomaly detection: Tweet-SCAN [Capdevila et al. 2015] – Crowd behavioral patterns Zheng, Y. 2011
- 21. GEOSRS: A SOCIAL RECOMMENDER SYSTEM 21 Joan Capdevila, Marta Arias, and Argimiro Arratia. "GeoSRS: A hybrid social recommender system for geolocated data." Information Systems (2015).
- 22. Motivation USERS
- 27. 27 System block diagram DATA EXTRACTION DATA PREPROCESSING TEXT MODELING RECOMMENDATION MIXER
- 28. 28 System block diagram DATA EXTRACTION DATA PREPROCESSING TEXT MODELING RECOMMENDATION MIXER
- 32. 32 Foursquare API HTTP METHODS – GET, POST, PUT ,DELETE RESOURCES – Venue, tip, user e.g. GET https://api.foursquare.com/v2/venues/40a55d80f964a52020f31ee3 ASPECTS – Tips of a venue, friends of a user e.g. GET https://api.foursquare.com/v2/venues/40a55d80f964a52020f31ee3/tips ACTIONS – Approve a friendship, like a venue e.g. POST https://api.foursquare.com/v2/venues/40a55d80f964a52020f31ee3/like
- 33. 33 Foursquare API App registration https://foursquare.com/developers/apps Obtain the Foursquare API credentials (Client ID and Client Secret) Access token Allows apps to make requests to Foursquare on behalf of a user Userless request Specify consumer key’s Client ID and Client Secret https://api.foursquare.com/v2/venues/search? ll=40.7,-74&client_id=XX&client_secret=ZZ&v=20151125 Authenticated request Specify access token https://api.foursquare.com/v2/users/self/checkins?oauth_token=AA
- 34. 34 Foursquare API Technical Limitations Userless requests to venues/ resource = 5.000 request/hour Userless requests to other resources = 500 request/hour Authenticated requests = 500 request/hour*token
- 36. 36 Data Extraction Goal: extract all tips from venues in Manhattan (New York) Medium: – aspect: venues/VENUE_ID/tips – resource: venues/search(sw, ne) Limitations: – 5000 request/hour – at most 50 venues per request SW NE
- 40. 40 Quadtree algorithm In each Quadcell at the tree leaves, there are at most 50 venues. Through venues/VENUE_ID/tips, we now retrieve the tips for this venue Each tip is linked to a VENUE_ID and USER_ID We now have a database of triplets (USER, TIPS, VENUE) to perform recommendation
- 42. 42 Collaborative Recommendation Collaborative recommendation based on tips’ sentiment Positive
- 43. 43 Content-based Recomendation Content-based recommendation based on tips’ content recommend
- 44. 44 Content-based Recomendation Content-based recommendation based on tips’ content Not recommend
- 45. 45 Hybridization Simple weighted hybridization technique Collaborative Branch fCOL Content-based Branch fCONT Hybrid f: fCOL +α fCONT
- 49. 49 Results Evaluation in terms of cumulated density functions (cdf) of the recommendation error
- 50. TWEET-SCAN: AN EVENT DISCOVERY TECHNIQUE 50 Joan Capdevila Jesús Cerquides Jordi Nin Jordi Torres. “Tweet-SCAN: An event discovery technique for geo-located tweets”. Proceedings of the 18th International Conference of the Catalan Association for Artificial Intelligence, 2015
- 51. Motivation
- 52. 52 Motivation CAN WE UNCOVER PHYSICAL WORLD EVENTS FROM TWEETS ?
- 53. 53 Examination of data We looked at several tweet dimension separately … from a dataset of tweets collected during “la Mercè” 2014 Spatial Temporal Textual
- 54. 54 Examination of data We looked at several tweet dimension separately … from a dataset of tweets collected during “la Mercè” 2014 Spatial Temporal Textual
- 55. 55 Examination of data Spatial and temporal
- 56. 56 Examination of data Spatial and temporal
- 57. 57 Tweet-SCAN WHAT ABOUT USING ALL 3 DIMENSIONS AT ONCE ?
- 58. 58 Tweet-SCAN Tweet-SCAN is a technique to discover events from geolocated Tweets. It allows to discover dense groups of Tweets which are close in space, time and textual meaning. These dense groups of Tweets are linked to physical world events Textual meaning is represented through probabilistic topic models Tweet-scan can be seen as an extension of the popular DBSCAN algorithm or a particular case of GDBSCAN
- 59. 59 Probabilistic topic modeling Fig. - Xuriguera et al. 2013 LDA - Blei et al. 2003 HDP - Teh et al. 2006 Latent Dirichlet Allocation (LDA) Hierarchical Dirichlet Process (HDP) – Non-parametric version of LDA
- 60. 60 Probabilistic topic modeling VAN VAN MARKET - 🚐🚎🍤🍱🍜 Mercat gastronòmada #lepetitbangkok @ Parc de la Ciutadella http://t.co/5CvnUFoIDa Topic Proportions: [(1, 0.30002802458675537), (11,0.58330530874655417)]
- 61. 61 DBSCAN Density-based Spatial Clustering for Applications with Noise Noise points params: Minpts=4, ε = Ester et al. 1996
- 62. 62 DBSCAN Density-based Spatial Clustering for Applications with Noise Core points params: Minpts=4, ε = ε Ester et al. 1996
- 63. 63 DBSCAN Density-based Spatial Clustering for Applications with Noise Core points params: Minpts=4, ε = ε Ester et al. 1996
- 64. 64 DBSCAN Density-based Spatial Clustering for Applications with Noise Border points params: Minpts=4, ε = ε Ester et al. 1996
- 65. 65 DBSCAN Density-based Spatial Clustering for Applications with Noise Border points params: Minpts=4, ε = ε Ester et al. 1996
- 66. 66 DBSCAN Density-based Spatial Clustering for Applications with Noise ε Noise point Border point Core point params: Minpts=4, ε = Ester et al. 1996
- 67. 67 Tweet-SCAN Neighborhood identification – ε1: spatial (m) – Euclidean distance – ε2: time (sec) – Euclidean distance – ε3: text – Jensen-Shannon distance (proper metric for prob. dist.) Cardinality of the neighborhood – MinPts – minimum number of neighbors (Tweets) – µ – minimum percentage of unique users in the neighborhood.
- 68. 68 Experimentation We used 45.623 tweets to unsupervisedly discover event-related tweets by means of Tweet-SCAN. We seek to understand the parameters role by comparing the resulting clusters against the 1.163 tagged event-related Tweets.
- 69. 69 Evaluation Extrinsic clustering metrics Amigo et al. 2008 Purity = Ci n max Precision Ci, Lj( )( ) i ∑ → Precision Ci, Lj( )= Ci ∩ L j Ci Precision(C,L)=9/10 Precision(C,L)=1/10 Precision(C,L)=0/10 Precision(C,L)=0/9 Precision(C,L)=8/9 Precision(C,L)=1/9 Precision(C,L)=0/9 Precision(C,L)=0/9 Precision(C,L)=9/9 C C C L L L
- 70. 70 Evaluation Extrinsic clustering metrics Amigo et al. 2008 Purity = Ci n max Precision Ci, Lj( )( ) i ∑ → Precision Ci, Lj( )= Ci ∩ L j Ci Purity = 0.92 C C C L L L Precision(C,L)=9/10 Precision(C,L)=1/10 Precision(C,L)=0/10 Precision(C,L)=0/9 Precision(C,L)=8/9 Precision(C,L)=1/9 Precision(C,L)=0/9 Precision(C,L)=0/9 Precision(C,L)=9/9
- 71. 71 Evaluation Extrinsic clustering metrics Amigo et al. 2008 Purity = Ci n max Precision Ci, Lj( )( ) i ∑ → Precision Ci, Lj( )= Ci ∩ L j Ci Purity = 1
- 72. 72 Evaluation Extrinsic clustering metrics Amigo et al. 2008 Recall(C,L)=9/9 Recall(C,L)=0/9 Recall(C,L)=0/9 Recall(C,L)=1/9 Recall(C,L)=8/9 Recall(C,L)=0/9 Recall(C,L)=0/10 Recall(C,L)=1/10 Recall(C,L)=9/10 InvPurity = Li n max Recall Cj, Li( )( ) i ∑ → Recall Cj, Li( )= Li ∩C j Li C C C L L L
- 73. 73 Evaluation Extrinsic clustering metrics Amigo et al. 2008 InvPurity = Li n max Recall Cj, Li( )( ) i ∑ → Recall Cj, Li( )= Li ∩C j Li Recall(C,L)=9/9 Recall(C,L)=0/9 Recall(C,L)=0/9 Recall(C,L)=1/9 Recall(C,L)=8/9 Recall(C,L)=0/9 Recall(C,L)=0/10 Recall(C,L)=1/10 Recall(C,L)=9/10 InvPurity = 0.92 C C C L L L
- 74. 74 Evaluation Extrinsic clustering metrics Amigo et al. 2008 InvPurity = Li n max Recall Cj, Li( )( ) i ∑ → Recall Cj, Li( )= Li ∩C j Li InvPurity = 0.1
- 75. 75 Evaluation Extrinsic clustering metrics Amigo et al. 2008 InvPurity = Li n max Recall Cj, Li( )( ) i ∑ → Recall Cj, Li( )= Li ∩C j Li InvPurity = 1
- 76. 76 Evaluation Extrinsic clustering metrics which is the harmonic mean F(Li,Cj) is the harmonic mean of Precision(Cj,Li) and Recall(Cj,Li) Amigo et al. 2008 F = Li n max F Li, Cj( )( ) i ∑ →F Li, Cj( )= 2×Recall(Cj,Li )×Precision( Cj,Li ) Recall(Cj,Li )+ Precision( Cj,Li )
- 77. 77 Evaluation results ε1 = 250m, ε2 = 3600s, MinPts = 10, µ = 0.5
- 78. 78 Evaluation results ε1 = 250m, ε2 = 3600s, ε3 = 1, MinPts = 10, µ = 0.5
- 79. 79 Evaluation results ε1 = 250m, ε2 = 3600s, ε3 = 0.8, MinPts = 10, µ = 0.5
- 80. 80 Evaluation results Discovered Events ε3 = 1Tagged Events Mostra Vins (20-09-2014) Vanvan market (20-09-2014)
- 81. 81 Evaluation results Tagged Events Mostra Vins (20-09-2014) Vanvan market (20-09-2014) Discovered Events ε3 = 0.8
- 82. 82 Evaluation results ε1=250m,ε2=3600s ε1=250m,ε2=1800sε1=500m,ε2=1800s ε1=500m,ε2=3600s Fopt = 0.64 ε3 = 1 Fopt = 0.693 ε3 = 0.9 Fopt = 0.62 ε3 = 0.65 Fopt = 0.53 ε3 = 0.9
- 83. CONCLUSIONS 83
- 84. Conclusions The birth of social networks is one of the major causes of current levels of digitalized personal data. Social networks have kept the doors opened to the developer community in order to stimulate the creation of apps. This “openness” has been materialized with RESTful APIs, that enables communication between third party apps and social networks. Through these APIs we are able to access vast amounts of data, develop and validate machine learning tools. However, technical and legal limitations have to be taken into account to build functional applications.
- 85. 85 Conclusions Location-based social networks enable to bridge the virtual and physical world. Classical application such as recommender systems have to be reconsidered to take into account this new dimension. Recommendation from textual reviews is feasible and hybridization improves performance. Data from SN can be very biased by their own services in the SN (e.g. by their own RS). Other novel application, such as event discovery, gain meaning with LBSNs. Event discovery has to consider textual dimension to uncover meaningful events
- 86. FUTURE TRENDS 86
- 87. 87 Internet of Things 2003 2010 2015 2020 In 2008, the number of things connected to the Internet exceeded the number of people on earth M. Swan 2014
- 88. 88 The Social Internet of Things (SIoT) Atzori 2012
- 89. 89 The internet of nano-things Akyildiz et al. 2010
- 91. 91 References Zheng, Yu. "Location-based social networks: Users." Computing with Spatial Trajectories. Springer New York, 2011. 243-276. Joan Capdevila, Marta Arias, and Argimiro Arratia. "GeoSRS: A hybrid social recommender system for geolocated data." Information Systems (2015). Joan Capdevila, Jesús Cerquides Jordi Nin Jordi Torres. “Tweet-SCAN: An event discovery technique for geo-located tweets”. Proceedings of the 18th International Conference of the Catalan Association for Artificial Intelligence, 2015 Blei, David M., Andrew Y. Ng, and Michael I. Jordan. "Latent dirichlet allocation." the Journal of machine Learning research 3 (2003): 993-1022.
- 92. 92 References Teh, Yee Whye, et al. "Hierarchical dirichlet processes." Journal of the american statistical association 101.476 (2006). Ester, Martin, et al. "A density-based algorithm for discovering clusters in large spatial databases with noise." Kdd. Vol. 96. No. 34. 1996. Amigó, Enrique, et al. "A comparison of extrinsic clustering evaluation metrics based on formal constraints." Information retrieval 12.4 (2009): 461-486. Melanie Swan. “Quantified Self Ideology. Personal data becomes Big Data” February 2014. Université Paris Descartes Akyildiz, Ian F., and Josep Miquel Jornet. "The internet of nano-things." Wireless Communications, IEEE 17.6 (2010): 58-63. Luigi Atzori A presentation on THE SOCIAL INTERNET OF THINGS University of Cagliari, Italy 2012