Corpus ID: 10356629

Extracting Diurnal Patterns of Real World Activity from Social Media

@inproceedings{Grinberg2013ExtractingDP,
  title={Extracting Diurnal Patterns of Real World Activity from Social Media},
  author={Nir Grinberg and Mor Naaman and Blake Shaw and Gilad Lotan},
  booktitle={ICWSM},
  year={2013}
}
In this study, we develop methods to identify verbal expressions in social media streams that refer to real-world activities. Using aggregate daily patterns of Foursquare checkins, our methods extract similar patterns from Twitter, extending the amount of available content while preserving high relevance. We devise and test several methods to extract such content, using time-series and semantic similarity. Evaluating on key activity categories available from Foursquare (coffee, food, shopping… Expand
Circadian Patterns in Twitter
  • M. T. Thij, Sandjai Bhulai, Peter Kampstra
  • Computer Science
  • 2014
TLDR
An algorithm is built to analyse the actual structure of the progressions of individual tweets through retweets in the Twittersphere and it is found that retweet trees show a star-like structure. Expand
High-resolution Temporal Representations of Alcohol and Tobacco Behaviors from Social Media Data
TLDR
It is found that time and frequency domain representations of behaviors on social media can provide meaningful and unique insights, and the types of behaviors for which the approach may be most useful. Expand
Forecasting high tide: Predicting times of elevated activity in online social media
TLDR
This work proposes three methods for behavior modeling: a simple seasonality approach based on time of-day and day-of-week, an autoregressive approachbased on aggregate fluctuations from seasonality, and an aggregation- of-individuals approachBased on modeling the behavior of individual users. Expand
Twitter Session Analytics: Profiling Users' Short-Term Behavioral Changes
TLDR
This work demonstrates that later in a session on Twitter, people prefer to perform simpler tasks, such as replying and retweeting others’ posts, rather than composing original messages, and they also tend to post shorter messages. Expand
Event-Related Crowd Activities on Social Media
Social media like Twitter has been prevalently used for observing the behaviors of a large number of people. The availability of such behavioral trace data leads to an emergent interest in studyingExpand
Understanding Context for Tasks and Activities
TLDR
This work proposes a method for extraction of an extensive set of open-vocabulary activities from Twitter and establishes spatiotemporal models of these activities at the time of posting, and solves predictive tasks centered on the relationship between activity and spatiotmporal context that are aimed at supporting an individual's information needs. Expand
Prediction of Elevated Activity in Online Social Media Using Aggregated and Individualized Models
Social media provides a powerful platform for influencers to broadcast content to a large audience of followers. In order to reach the greatest number of users, an important first step is to identifyExpand
Modeling User Behavior on Socio-Technical Systems: Patterns and Anomalies
TLDR
This thesis looks at two closely related problems i.e. modeling user behavior on social media platforms, and then using similarly generated models to detect abnormal and potentially fraudulent behavior. Expand
Mining location from social media: A systematic review
TLDR
This analysis of 690 papers across 20 social media platforms, focussing particularly on the method used for extraction of location information, discusses and compare extraction methods, and considers their accuracy and coverage. Expand
Analysing the interplay of location, language and links utilising geotagged Twitter content
TLDR
This work proposes text-based and network-based geolocation models, and compares them over benchmark datasets yielding state-of-theart performance, and shows that the joint models are able to achieve reasonable performance in minimal supervision scenarios, as often happens in real world datasets. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 30 REFERENCES
On the Study of Diurnal Urban Routines on Twitter
TLDR
It is shown that only a few cities currently provide the magnitude of content needed to support such across-day variability analysis for more than a few keywords, and within-day diurnal variability can help in comparing activities and finding similarities between cities. Expand
Comparing Twitter and Traditional Media Using Topic Models
TLDR
This paper empirically compare the content of Twitter with a traditional news medium, New York Times, using unsupervised topic modeling, and finds interesting and useful findings for downstream IR or DM applications. Expand
Characterizing Microblogs with Topic Models
TLDR
A scalable implementation of a partially supervised learning model (Labeled LDA) that maps the content of the Twitter feed into dimensions that correspond roughly to substance, style, status, and social characteristics of posts is presented. Expand
Patterns of temporal variation in online media
TLDR
This work develops the K-Spectral Centroid (K-SC) clustering algorithm that effectively finds cluster centroids with the authors' similarity measure and presents a simple model that reliably predicts the shape of attention by using information about only a small number of participants. Expand
Uncovering individual and collective human dynamics from mobile phone records
TLDR
The mean collective behavior at large scales is studied and it is shown that the interevent time of consecutive calls is heavy-tailed, which has implications for dynamics of spreading phenomena in social networks. Expand
When a city tells a story: urban topic analysis
TLDR
This paper applies a probabilistic topic model to obtain a decomposition of the stream of digital traces into a set of urban topics related to various activities of the citizens in the course of a week and describes an implementation architecture of the system, the main outputs of the analysis, and the derived exploratory visualisations. Expand
Rhythms of social interaction: messaging within a massive online network
TLDR
This paper studies the social net- work service Facebook, which began in early 2004 in select universities, but grew quickly to encompass a very large number of universities. Expand
Meme-tracking and the dynamics of the news cycle
TLDR
This work develops a framework for tracking short, distinctive phrases that travel relatively intact through on-line text; developing scalable algorithms for clustering textual variants of such phrases, and identifies a broad class of memes that exhibit wide spread and rich variation on a daily basis. Expand
The Livehoods Project: Utilizing Social Media to Understand the Dynamics of a City
TLDR
This work introduces a clustering model and research methodology for studying the structure and composition of a city on a large scale based on the social media its residents generate, and applies this new methodology to data from approximately 18 million check-ins collected from users of a location-based online social network. Expand
ET-LDA: Joint Topic Modeling for Aligning Events and their Twitter Feedback
TLDR
A joint Bayesian model that performs topic modeling and event segmentation in one unified framework is developed and evaluated both quantitatively and qualitatively on two large-scale tweet datasets associated with two events from different domains to show that it improves significantly over baseline models. Expand
...
1
2
3
...