A topic model based framework for identifying the distribution of demand for relief supplies using social media data

Natural disasters have caused substantial economic losses and numerous casualties. The demand analysis of relief supplies is the premise and basis for efficient relief operations after disasters. With the widespread use of social media, it has become a vital channel for people to report their demand for relief supplies and provides a way to obtain information on disaster areas. Therefore, we present a topic model-based framework and establish a demand dictionary and a gazetteer that aims to identify the spatial distribution of the demand for relief supplies by using social media data. Taking the 2013 Typhoon Haiyan (also called Yolanda) as a case study, we identify the potential topics of tweets with the biterm topic model, screen the tweets related to demands, and obtain the demand and location information from tweets to study the distribution of the relief supplies needs. The results show that, based on the demand dictionary, a gazetteer and the biterm topic model, the effective demand for relief supplies can be extracted from tweets. The proposed framework is feasible for the identification of accurate demand information and its distribution. Further, this framework can be applied to other types of disaster responses and can facilitate relief operations.File introduction：BTM_Model_window.py：The window program of the BTM model will call the methods involved in the BTM model.BTMModel.py：BTM method code.Biterm.py：Classes in BTMtest_tweet.csv：Tweets related to Typhoon Haiyan (used in BTM_Model_window.py, test data, not complete data).stemtext.py：Used for tweet extraction (input data example: demand_tweets.xlsx; output data example: tem_result.xls)wordfrequency.py：Used to calculate the frequency of tweets.main_dis.py：Call Distinguish.py to extract rescue supplies and location information from tweets (input data example: demand_tweets.xlsx, DIC.xlsx; output data example: result.xlsx)Distinguish.py：Method file.