A large-scale empirical study of geotagging behavior on Twitter

Huang, Binxuan; Carley, Kathleen M.

doi:10.1145/3341161.3342870

Cited by 41 publications

(40 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to achieve this aim, the tweet terms are compared with the words contained in a set of dictionaries: if the tweet term is found in one of the used dictionaries, it is removed. The used dictionaries are: 1) the dictionary of the language of the tweet 3 ; 2) the English dictionary 4 because the use of anglicisms is a common routine; 3) a dictionary of the Internet slang 5 containing the most common abbreviations used in the Internet. The tweet terms that are not filtered are considered to be names for candidate locations.…”

Section: F Candidate Location Computationmentioning

confidence: 99%

“…Unfortunately, identifying the location where events are taking place is one of the biggest challenges in this new field of research. The complexity of event geo-localization is related to a set of factors which include: a) not all tweets written during the discussion of an event contain information about the location of that event; b) only a very small part of the tweets (about 2% of the posted tweets [5]) are geo-located, indeed, not necessarily a user in describing an event must also indicate the place where it occurred; c) the information contained in the tweets may be inconsistent (e.g., inaccurate, badly written, ambiguous). Because of its underlying complexity, in the literature, only few efforts, characterized by crucial limitations, have been carried out to address the geo-localization problem.…”

Section: Introductionmentioning

confidence: 99%

“…https://github.com/michmech/lemmatizationlists/blob/master/lemmatization-it.txt4 https://github.com/michmech/lemmatizationlists/blob/master/lemmatization-en.txt5 https://www.urbandictionary.com/…”

mentioning

confidence: 99%

See 2 more Smart Citations

Automatic Event Geo-Location in Twitter

et al. 2020

View full text Add to dashboard Cite

Twitter is currently one of the most popular platforms for disseminating information about events happening around the world. Especially but not only for emergency events, it is crucial to know when and where the events are taking place. Unfortunately, identifying the geo-location of an event discussed in Twitter is a very challenging task mainly due to the brevity of the messages (i.e., tweets) and their subjective nature. In the literature, some efforts have been made to address this task, but they are characterized by substantial limitations such as the use of exclusively text analysis techniques, or the need for keywords or possible candidate locations. This paper proposes a new process for automatic event geo-localization which relies on both textual and spatial/temporal use of content posted on Twitter without using some prior knowledge about the event to be located. As shown by experimental results, our proposal achieves a good accuracy rate and outperforms two well-known baseline approaches related to the geo-location of events in Twitter.

show abstract

Section: F Candidate Location Computationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Event Geo-Location in Twitter

et al. 2020

View full text Add to dashboard Cite

show abstract

“…These pioneering studies often used field work data from a handful of individuals and focused on small sets of carefully chosen features, often phonological. Inspired by this early work, researchers have used geographically tagged social media data from hundreds of thousands of users to predict user location (Paul and Dredze, 2011;Amitay et al, 2004;Han et al, 2014;Rahimi et al, 2017;Huang and Carley, 2019b;Tian et al, 2020;Zhong et al, 2020) or to develop language identification tools (Lui and Baldwin, 2012;Zubiaga et al, 2016;Jurgens et al, 2017a;Dunn and Adams, 2020). Whether it is possible at all to predict the micro-varieties 2 of the same general 1 Our labeled data and models will be available at: https: //github.com/UBC-NLP/microdialects.…”

Section: Introductionmentioning

confidence: 99%

Toward Micro-Dialect Identification in Diaglossic and Code-Switched Environments

Abdul-Mageed

Zhang

Elmadany

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Although prediction of dialects is an important language processing task, with a wide range of applications, existing work is largely limited to coarse-grained varieties. Inspired by geolocation research, we propose the novel task of Micro-Dialect Identification (MDI) and introduce MARBERT, a new language model with striking abilities to predict a fine-grained variety (as small as that of a city) given a single, short message. For modeling, we offer a range of novel spatially and linguistically-motivated multi-task learning models. To showcase the utility of our models, we introduce a new, large-scale dataset of Arabic micro-varieties (low-resource) suited to our tasks. MARBERT predicts micro-dialects with 9.9% F 1 , ∼ 76× better than a majority class baseline. Our new language model also establishes new state-ofthe-art on several external tasks. 1

show abstract

“…Despite these advantages, one major issue that hinders the usability of Twitter data is the lack of geolocation information. Only 1-3% of tweets has GPS-coordinates (Huang and Carley, 2019). Response authorities and humanitarian organizations heavily rely on geolocation information for both situational awareness and response tasks.…”

Section: Introductionmentioning

confidence: 99%

Are We Ready for this Disaster? Towards Location Mention Recognition from Crisis Tweets

Suwaileh¹,

Imran²,

Elsayed³

et al. 2020

Proceedings of the 28th International Conference on Computational Linguistics

View full text Add to dashboard Cite

The widespread usage of Twitter during emergencies has provided a new opportunity and timely resource to crisis responders for various disaster management tasks. Geolocation information of pertinent tweets is crucial for gaining situational awareness and delivering aid. However, the majority of tweets do not come with geoinformation. In this work, we focus on the task of location mention recognition from crisis-related tweets. Specifically, we investigate the influence of different types of labeled training data on the performance of a BERT-based classification model. We explore several training settings such as combing in-and out-domain data from news articles and general-purpose and crisis-related tweets. Furthermore, we investigate the effect of geospatial proximity while training on near or far-away events from the target event. Using five different datasets, our extensive experiments provide answers to several critical research questions that are useful for the research community to foster research in this important direction. For example, results show that, for training a location mention recognition model, Twitter-based data is preferred over general-purpose data; and crisis-related data is preferred over generalpurpose Twitter data. Furthermore, training on data from geographically-nearby disaster events to the target event boosts the performance compared to training on distant events.

show abstract

A large-scale empirical study of geotagging behavior on Twitter

Cited by 41 publications

References 27 publications

Automatic Event Geo-Location in Twitter

Automatic Event Geo-Location in Twitter

Toward Micro-Dialect Identification in Diaglossic and Code-Switched Environments

Are We Ready for this Disaster? Towards Location Mention Recognition from Crisis Tweets

Contact Info

Product

Resources

About