Dataset Information

Sci-Fin: Visual Mining Spatial and Temporal Behavior Features from Social Media.

ABSTRACT: Check-in records are usually available in social services, which offer us the opportunity to capture and analyze users' spatial and temporal behaviors. Mining such behavior features is essential to social analysis and business intelligence. However, the complexity and incompleteness of check-in records bring challenges to achieve such a task. Different from the previous work on social behavior analysis, in this paper, we present a visual analytics system, Social Check-in Fingerprinting (Sci-Fin), to facilitate the analysis and visualization of social check-in data. We focus on three major components of user check-in data: location, activity, and profile. Visual fingerprints for location, activity, and profile are designed to intuitively represent the high-dimensional attributes. To visually mine and demonstrate the behavior features, we integrate WorldMapper and Voronoi Treemap into our glyph-like designs. Such visual fingerprint designs offer us the opportunity to summarize the interesting features and patterns from different check-in locations, activities and users (groups). We demonstrate the effectiveness and usability of our system by conducting extensive case studies on real check-in data collected from a popular microblogging service. Interesting findings are reported and discussed at last.

SUBMITTER: Pu J

PROVIDER: S-EPMC5191173 | biostudies-literature | 2016 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Sci-Fin: Visual Mining Spatial and Temporal Behavior Features from Social Media.

Pu Jiansu J Teng Zhiyao Z Gong Rui R Wen Changjiang C Xu Yang Y

Sensors (Basel, Switzerland) 20161220 12

Check-in records are usually available in social services, which offer us the opportunity to capture and analyze users' spatial and temporal behaviors. Mining such behavior features is essential to social analysis and business intelligence. However, the complexity and incompleteness of check-in records bring challenges to achieve such a task. Different from the previous work on social behavior analysis, in this paper, we present a visual analytics system, Social Check-in Fingerprinting (Sci-Fin) ...[more]

PMID: 27999398

Similar Datasets

Project description:BackgroundIncorporating social media features into digital behavior change interventions (DBCIs) has the potential to contribute positively to their success. However, the lack of clear design principles to describe and guide the use of these features in behavioral interventions limits cross-study comparisons of their uses and effects.ObjectiveThe aim of this study was to provide a systematic review of DBCIs targeting modifiable behavioral risk factors that have included social media features as part of their intervention infrastructure. A taxonomy of social media features is presented to inform the development, description, and evaluation of behavioral interventions.MethodsSearch terms were used in 8 databases to identify DBCIs that incorporated social media features and targeted tobacco smoking, diet and nutrition, physical activities, or alcohol consumption. The screening and review process was performed by 2 independent researchers.ResultsA total of 5264 articles were screened, and 143 articles describing a total of 134 studies were retained for full review. The majority of studies (70%) reported positive outcomes, followed by 28% finding no effects with regard to their respective objectives and hypothesis, and 2% of the studies found that their interventions had negative outcomes. Few studies reported on the association between the inclusion of social media features and intervention effect. A taxonomy of social media features used in behavioral interventions has been presented with 36 social media features organized under 7 high-level categories. The taxonomy has been used to guide the analysis of this review.ConclusionsAlthough social media features are commonly included in DBCIs, there is an acute lack of information with respect to their effect on outcomes and a lack of clear guidance to inform the selection process based on the features' suitability for the different behaviors. The proposed taxonomy along with the set of recommendations included in this review will support future research aimed at isolating and reporting the effects of social media features on DBCIs, cross-study comparisons, and evaluations.

Dataset Information

Sci-Fin: Visual Mining Spatial and Temporal Behavior Features from Social Media.

Publications

Sci-Fin: Visual Mining Spatial and Temporal Behavior Features from Social Media.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets