scholarly journals A Varied Density-based Clustering Approach for Event Detection from Heterogeneous Twitter Data

2019 ◽  
Vol 8 (2) ◽  
pp. 82 ◽  
Author(s):  
Zeinab Ghaemi ◽  
Mahdi Farnaghi
Keyword(s):  
Spatial Heterogeneity ◽  
Event Detection ◽  
Spatial Clustering ◽  
Spline Interpolation ◽  
The United States ◽  
Spatial Proximity ◽  
Twitter Data ◽  
Density Based Clustering ◽  
Exponential Spline ◽  
Comparison Of The Results

Extracting the latent knowledge from Twitter by applying spatial clustering on geotagged tweets provides the ability to discover events and their locations. DBSCAN (density-based spatial clustering of applications with noise), which has been widely used to retrieve events from geotagged tweets, cannot efficiently detect clusters when there is significant spatial heterogeneity in the dataset, as it is the case for Twitter data where the distribution of users, as well as the intensity of publishing tweets, varies over the study areas. This study proposes VDCT (Varied Density-based spatial Clustering for Twitter data) algorithm that extracts clusters from geotagged tweets by considering spatial heterogeneity. The algorithm employs exponential spline interpolation to determine different search radiuses for cluster detection. Moreover, in addition to spatial proximity, textual similarities among tweets are also taken into account by the algorithm. In order to examine the efficiency of the algorithm, geotagged tweets collected during a hurricane in the United States were used for event detection. The output clusters of VDCT have been compared to those of DBSCAN. Visual and quantitative comparison of the results proved the feasibility of the proposed method.

scholarly journals Use of Twitter Data to Improve Zika Virus Surveillance in the United States during the 2016 Epidemic

2018 ◽  
Vol 2018 (1) ◽  
Author(s):  
Shahir Masri ◽  
Jianfeng Jia ◽  
Chen Li ◽  
Guofa Zhou ◽  
Ming-Chieh Lee ◽  
...  
Keyword(s):  
United States ◽  
Zika Virus ◽  
The United States ◽  
Virus Surveillance ◽  
Twitter Data

Using Volunteered Geographic Information to Assess the Spatial Distribution of West Nile Virus in Detroit, Michigan

2013 ◽  
pp. 1170-1182
Author(s):  
Kevin P. McKnight ◽  
Joseph P. Messina ◽  
Ashton M. Shortridge ◽  
Meghan D. Burns ◽  
Bruce W. Pigozzi
Keyword(s):  
West Nile Virus ◽  
Spatial Clustering ◽  
Clustering Algorithms ◽  
The United States ◽  
Data Availability ◽  
Limited Information ◽  
Hotspot Detection ◽  
West Nile ◽  
Dead Bird ◽  
Global And Local

West Nile Virus is a vector-borne flavivirus that affects mainly birds, horses, and humans. The disease emerged in the United States in 1999 and by 2001 had reached Michigan. In clinical human cases, the most common symptoms are fever, weakness, nausea, headache, and changes in mental state. The crow is the most common wildlife host in the life cycle of the virus. The state of Michigan, through the Michigan Department of Community Health, collected the spatial locations of over 8,000 dead birds (Corvidae), statewide, during 2002. The large number of samples made spatial and temporal hotspot detection possible. However, the volunteer reporting method produced a dataset with a direct correlation between the numbers and locations of the dead birds and human population density and accurately identifying hotspots remains a challenge. Geographic variation in dead bird intensity was modeled using both global and local spatial clustering algorithms. Statistical models identified overall spatial structure and local clustering. Identification of hotspots was confounded by limited information about the collection procedures, data availability and quality, and the limitations of each method.

scholarly journals THE EFFECT OF LANGUAGE ON PREPARATION FOR OLD AGE: EVIDENCE FROM CROSS-CULTURAL SURVEY AND TWITTER DATA

2019 ◽  
Vol 3 (Supplement_1) ◽  
pp. S976-S976
Author(s):  
Amber Xuqian Chen ◽  
Helene H Fung
Keyword(s):  
Old Age ◽  
Living Arrangement ◽  
Future Orientation ◽  
The United States ◽  
Cross Cultural ◽  
Future Tense ◽  
Time Discounting ◽  
Twitter Data ◽  
The Future ◽  
Future Project

Abstract We aimed to further investigate the linguistic-savings hypothesis (Chen, 2013) in the field of aging, which maintains that when languages grammatically divide the future and the present (e.g. English and Czech), speakers tend to behave less future-oriented than those speaking languages that do not mark future tense (e.g. German and Chinese). In the 2018 wave of Aging as Future Project, 2,042 participants from the United States, Germany, Czech Republic, Hong Kong and Taiwan (18-93 year, Mean age= 55.47, 55.61% female) completed online questionnaires. The results supported the hypothesis that people speaking future-less languages tended to perceive the timing of preparation for old age closer to the present in terms of finance, living arrangement, nursing care, and loneliness, they also took action earlier and performed more relevant activities. Furthermore, the association between language and preparation timing was more salient in older adults than younger counterparts. And path analysis revealed that time discounting was a significant predictor (P=0.049) for the future-oriented behavior. Hence, speakers of futureless languages will view the future as temporally closer to the present, causing them to discount the future less and prepare for old age actively. Using LIWC 2017, we then analyzed community-level of future orientation with 80 million Tweets across countries and replicated our principal result through that usage of future-oriented languages partly predicted prevalence of health behaviors. The findings indicate that language not only shape people's own future-oriented outcomes, through decreasing time discounting, but also influence population health as a whole.

Sign in / Sign up

Export Citation Format

Share Document