Fine-grained Geolocation Prediction of Tweets with Human Machine Collaboration

Abstract

Twitter is a useful resource to analyze peoples' opinions on various topics. Often these topics are correlated or associated with locations from where these Tweet posts are made. For example, restaurant owners may need to know where their target customers eat with respect to the sentiment of the posts made related to food, policy planners may need to analyze citizens' opinion on relevant issues such as crime, safety, congestion, etc. with respect to specific parts of the city, or county or state. As promising as this is, less than 1% of the crawled Tweet posts come with geolocation tags. That makes accurate prediction of Tweet posts for the non geo-tagged tweets very critical to analyze data in various domains. In this research, we utilized millions of Twitter posts and end-users domain expertise to build a set of deep neural network models using natural language processing (NLP) techniques, that predicts the geolocation of non geo-tagged Tweet posts at various level of granularities such as neighborhood, zipcode, and longitude with latitudes. With multiple neural architecture experiments, and a collaborative human-machine workflow design, our ongoing work on geolocation detection shows promising results that empower end users to correlate relationship between variables of choice with the location information.

Fine-grained location prediction of non geo-tagged tweets

“…In [4] authors utilized millions of Twitter posts and end-users domain expertise to build a set of deep neural network models using natural language processing (NLP) techniques, that predicts the geolocation of non geo-tagged Tweet posts. Their contribution was to provide a novel text modeling approach informed with feedback to predict the geolocation information.…”

“…We enrich our data using two different ways, using NER extraction and embedding calculation. 4 https://python-overpy.readthedocs.io/en/latest/ To extract POIs mentioned in the tweet text we need the help of NLP techniques, thus we used the NER model. Specifically, we used the model developed for NER (Named Entity Recognition) that is found on huggingface 5 6 , which has around 88.5% overall precision.…”