Twitter Geolocation

Bakerman, Jordan; Pazdernik, Karl; Fairchild, Geoffrey; Bahran, Rian

doi:10.1145/3178112

Cited by 35 publications

(13 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study was exploratory in nature and collected social media messages for which latitude and longitude coordinates could be collected from the Twitter API, but this data collection methodology is limited to collecting messages from Twitter users that enabled geolocation, a specific limitation to generating a more generalizable dataset on Twitter as it is estimated that only 1% of all tweets are geocoded (48,49). Hence, the dataset used in this study after filtering for keywords was small and likely biased, limiting the generalizability of results.…”

Section: Limitationsmentioning

confidence: 99%

Characterizing Self-Reported Tobacco, Vaping, and Marijuana-Related Tweets Geolocated for California College Campuses

Cuomo

Purushothaman

Li³

et al. 2021

Front. Public Health

View full text Add to dashboard Cite

Introduction: College-aged youth are active on social media yet smoking-related social media engagement in these populations has not been thoroughly investigated. We sought to conduct an exploratory infoveillance study focused on geolocated data to characterize smoking-related tweets originating from California 4-year colleges on Twitter.Methods: Tweets from 2015 to 2019 with geospatial coordinates in CA college campuses containing smoking-related keywords were collected from the Twitter API stream and manually annotated for discussions about smoking product type, sentiment, and behavior.Results: Out of all tweets detected with smoking-related behavior, 46.7% related to tobacco use, 50.0% to marijuana, and 7.3% to vaping. Of these tweets, 46.1% reported first-person use or second-hand observation of smoking behavior. Out of 962 tweets with user sentiment, the majority (67.6%) were positive, ranging from 55.0% for California State University, Long Beach to 95.8% for California State University, Los Angeles.Discussion: We detected reporting of first- and second-hand smoking behavior on CA college campuses representing possible violation of campus smoking bans. The majority of tweets expressed positive sentiment about smoking behaviors, though there was appreciable variability between college campuses. This suggests that anti-smoking outreach should be tailored to the unique student populations of these college communities.Conclusion: Among tweets about smoking from California colleges, high levels of positive sentiment suggest that the campus climate may be less receptive to anti-smoking messages or adherence to campus smoking bans. Further research should investigate the degree to which this varies by campuses over time and following implementation of bans including validating using other sources of data.

show abstract

Section: Limitationsmentioning

confidence: 99%

Characterizing Self-Reported Tobacco, Vaping, and Marijuana-Related Tweets Geolocated for California College Campuses

Cuomo

Purushothaman

Li³

et al. 2021

Front. Public Health

View full text Add to dashboard Cite

show abstract

“…Moreover, few users use geotagging (e.g., due to privacy issues) (Schulz et al, 2013), which reduces greatly the impact of supervised learning WD methods. Some recent studies adopt hybrid approaches, combining: WD and FN (e.g, (Rahimi et al, 2015;Bakerman et al, 2018)); WD and features derived from user account Metadata (MD) (Ozdikis et al, 2016;Dredze et al, 2013;Schulz et al, 2013); and WD, FN and MD (Williams et al, 2017).…”

Section: Related Workmentioning

confidence: 99%

“…In contrast with several state-of-the-art works (e.g., Celik & Dokuz, 2018;Do et al, 2018;Huang & Carley, 2019;Paule et al, 2019;Ozdikis et al, 2019), a pure unsupervised WD approach is adopted and thus no geographic labeled data (e.g., tweets or user location profiles) is required, only historical tweet nouns and GT data. Moreover, we do not use LIW, as adopted in (Ozdikis et al, 2016;Williams et al, 2017;Bakerman et al, 2018;Shahraki et al, 2019), since LIW often assumes finite and rather static set of locations, typically associated to small world regions. Instead, we use tweet nouns, which can be dynamically updated and that can refer to geographic words and also other terms with a location context (e.g., events, people or organizations).…”

Section: Most Research Work That Focus On Geographic Coordinates (Gcmentioning

confidence: 99%

A Google Trends spatial clustering approach for a worldwide Twitter user geolocation

Zola

Ragno²,

Cortez

2020

Information Processing & Management

View full text Add to dashboard Cite

User location data is valuable for diverse social media analytics. In this paper, we address the non-trivial task of estimating a worldwide city-level Twitter user location considering only historical tweets. We propose a purely unsupervised approach (no location data is used) that is based on a synthetic geographic sampling of Google Trends (GT) city-level frequencies of tweet nouns and three clustering algorithms. The approach was validated empirically by using a recently collected dataset, with 3,268 worldwide city-level locations of Twitter users, obtaining competitive results when compared with a state-of-the-art Word Distribution (WD) user location estimation method. The best overall results were achieved by the GT noun (GTN) DBSCAN (GTN-DB) method, which is computationally fast, and correctly predicts the ground truth locations of 15%, 23%, 39% and 58% of the users for tolerance distances of 250 km, 500 km, 1,000 km and 2,000 km.

show abstract

“…Hence, it is possible that not all non-English COVID-19 selling posts were detected, though non-English signal posts may contain the features subject to classification. The presence of non-English language posts and characters likely indicates that signal posts targeted non-US audiences and social media users, even though the majority of users on both of these platforms are located in the United States [29][30][31]. However, determining more precise geolocation of users was difficult as only 87 tweets and 134 Instagram posts had geotagged information available.…”

Section: Covid-19 Seller Metadata Characteristicsmentioning

confidence: 99%

Big Data, Natural Language Processing, and Deep Learning to Detect and Characterize Illicit COVID-19 Product Sales: Infoveillance Study on Twitter and Instagram (Preprint)

Mackey¹,

Li²,

Purushothaman³

et al. 2020

Preprint

View full text Add to dashboard Cite

BACKGROUND The COVID-19 pandemic is perhaps the greatest global health challenge of the last century. Accompanying this pandemic is a parallel “infodemic”, including the online marketing and sale of unapproved, illegal and counterfeit COVID-19 health products, including testing kits, treatments, and other questionable “cures”. Enabling proliferation of this content is growing ubiquity of Internet-based technologies, including popular social media platforms that now have billions of global users. OBJECTIVE To collect, analyze, identify and enable reporting of suspected fake, counterfeit, and unapproved COVID-19-related healthcare products from Twitter and Instagram. METHODS The study was conducted in two phases beginning with collection of COVID-19-related Twitter and Instagram posts using a combination of web scraping on Instagram and filtering the public streaming Twitter API for keywords associated with suspect marketing and sale of COVID-19 products. The second phase involved data analysis using natural language processing and deep learning to identify potential sellers that were then manually annotated for characteristics of interest. We also visualized illegal selling posts on a customized data dashboard to enable public health intelligence. RESULTS We collected a total of 6,029,323 tweets and 204,597 Instagram posts filtered for terms associated with suspect marketing and sale of COVID-19 health products from March – April for Twitter and February – May for Instagram. After applying our NLP and deep learning approaches, we identified 1,271 tweets and 596 Instagram posts associated with questionable sales of COVID-19-related products. Generally, product introduction came in three waves, with the first consisting of questionable immunity-boosting treatments, a second involving suspect testing kits, and a third of pharmaceuticals that have not been approved for COVID-19 treatment, with these waves following news coverage about product developments. Other major themes detected included accounts with descriptive COVID-19 accounts, products offered in different languages, various claims of product credibility, unsubstantiated products, unapproved testing modalities, and different payment and seller contact methods. CONCLUSIONS Results from this study provide initial insight into one front of the “infodemic” fight against COVID-19 by characterizing what types of health products, selling claims and types of sellers are active on two popular social media platforms. The challenge of combating this form of cybercrime is likely to continue as the pandemic progresses and more people seek access to COVID-19 information and treatment. Visualization of detected sellers and identification of their social media communication strategies can provide needed intelligence to public health agencies, regulatory authorities, legitimate manufacturers, and technology platforms to better remove and prevent this content from harming the public.

show abstract

Twitter Geolocation

Cited by 35 publications

References 23 publications

Characterizing Self-Reported Tobacco, Vaping, and Marijuana-Related Tweets Geolocated for California College Campuses

Characterizing Self-Reported Tobacco, Vaping, and Marijuana-Related Tweets Geolocated for California College Campuses

A Google Trends spatial clustering approach for a worldwide Twitter user geolocation

Big Data, Natural Language Processing, and Deep Learning to Detect and Characterize Illicit COVID-19 Product Sales: Infoveillance Study on Twitter and Instagram (Preprint)

Contact Info

Product

Resources

About