Paper Details

The increase of interest in using social media as a source for research has motivated tackling the challenge ofautomatically geolocating messages , given the lack of explicit location information in the majority of messages. Incontrast to much previous work that has focused on location classification of messages restricted to a specific country,here we undertake the task in a broader context by classifying global messages at the country level, which is so farunexplored in a real-time scenario. We analyse the extent to which a tweet’s country of origin can be determined bymaking use of eight tweet-inherent features for classification. Furthermore, we use two datasets, collected a year apartfrom each other, to analyse the extent to which a model trained from historical messages can still be leveraged forclassification of new messages. With classification experiments on all 217 countries in our datasets, as well as on the top25 countries, we offer some insights into the best use of tweet-inherent features for an accurate country-levelclassification of messages. We find that the use of a single feature, such as the use of tweet content alone – the mostwidely used feature in previous work – leaves much to be desired. Choosing an appropriate combination of both tweetcontent and metadata can actually lead to substantial improvements of between 20% and 50%. We observe that tweetcontent, the user’s self-reported location and the user’s real name, all of which are inherent in a tweet and available in areal-time scenario, are particularly useful to determine the country of origin. We also experiment on the applicability ofa model trained on historical messages to classify new messages, finding that the choice of a particular combination offeatures whose utility does not fade over time can actually lead to comparable performance, avoiding the need to retrain.However, the difficulty of achieving accurate classification increases slightly for countries with multiple commonalities,especially for English and Spanish speaking countries.

Arockia Selvaraj.A, Dhinesh Kumar.S, Dhivaharan.S, Prakash.A, SureshKumar.S, “TOWARDS REAL TIME,COUNTRY LEVEL LOCATION CLASSIFICATION OF WORLDWIDE- FACEBOOK”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 5, Issue 3, pp. 714-718, March 2018.