Mining location information from users' spatio-temporal data

Jenson, Sage; Reeves, Majerle; Tomasini, Marcello; Menezes, Ronaldo

doi:10.1109/uic-atc.2017.8397519

Cited by 3 publications

(1 citation statement)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Spatial entities refer to locations of interest which witness the aggregation of people. ey are usually identi ed using a clustering algorithm [14,15] and are in the form of groups of tweet locations. For the publish time of tweets, L G -CM uses the features like hour-of-day and day-of-week as temporal entities.As for textual entities in tweets, we address the extracted keywords and phrases a er removing stopwords.…”

Section: Introductionmentioning

confidence: 99%

Learning Embeddings of Spatial, Textual and Temporal Entities in Geotagged Tweets

Wei

Anjaria

Samet

2019

Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems

View full text Add to dashboard Cite

With online social networks being extended to geographical space, location context plays a key role in many applications such as local event detection and location recommendation. Geotagged tweets in Twi er serve as an invaluable source to understand people's activities in urban space. Analyzing geotagged tweets to identify implicit contexts among location, time and text is an interesting problem. In this paper, we present L G -CM, a methodology for L earning embeddings of Ge tagged tweets for Cross-Modal search such as locations, time units (hour-of-day and day-of-week) and textual words in tweets. e resulting compact vector representations of these entities make it easy to perform searches like " nd which locations are mostly related to the given topics". In L G -CM, we rst build a graph of entities extracted from tweets in which each edge carries the weight of co-occurrences between two entities. e embeddings of graph nodes are then learned in the same latent space under the guidance of approximating stationary residing probabilities between nodes which are computed using personalized random walk procedures. We evaluate L G -CM on datasets of New York City and Los Angeles, showing that the proposed method generally outperforms competitive baseline approaches.

show abstract

Section: Introductionmentioning

confidence: 99%

Learning Embeddings of Spatial, Textual and Temporal Entities in Geotagged Tweets

Wei

Anjaria

Samet

2019

Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems

View full text Add to dashboard Cite

show abstract

Significance of Linguistic Indicators for Location Prediction

Rehman

Malik

Faisal

2019

2019 22nd International Multitopic Conference (INMIC)

View full text Add to dashboard Cite

Where you go is who you are: a study on machine learning based semantic privacy attacks

Wiedemann,

Janowicz,

Raubal

et al. 2024

J Big Data

View full text Add to dashboard Cite

Concerns about data privacy are omnipresent, given the increasing usage of digital applications and their underlying business model that includes selling user data. Location data is particularly sensitive since they allow us to infer activity patterns and interests of users, e.g., by categorizing visited locations based on nearby points of interest (POI). On top of that, machine learning methods provide new powerful tools to interpret big data. In light of these considerations, we raise the following question: What is the actual risk that realistic, machine learning based privacy attacks can obtain meaningful semantic information from raw location data, subject to inaccuracies in the data? In response, we present a systematic analysis of two attack scenarios, namely location categorization and user profiling. Experiments on the Foursquare dataset and tracking data demonstrate the potential for abuse of high-quality spatial information, leading to a significant privacy loss even with location inaccuracy of up to 200 m. With location obfuscation of more than 1 km, spatial information hardly adds any value, but a high privacy risk solely from temporal information remains. The availability of public context data such as POIs plays a key role in inference based on spatial information. Our findings point out the risks of ever-growing databases of tracking data and spatial context data, which policymakers should consider for privacy regulations, and which could guide individuals in their personal location protection measures.

show abstract

Mining location information from users' spatio-temporal data

Cited by 3 publications

References 38 publications

Learning Embeddings of Spatial, Textual and Temporal Entities in Geotagged Tweets

Learning Embeddings of Spatial, Textual and Temporal Entities in Geotagged Tweets

Significance of Linguistic Indicators for Location Prediction

Where you go is who you are: a study on machine learning based semantic privacy attacks

Contact Info

Product

Resources

About