Hypothesis Testing of Tweet Text Using NLP

Abstract

Natural Language processing applications such as sentiment analysis, spam detection, and stance detection extract the author’s emotions, feelings, and categorizations such as favor or denial from a piece of text sentences or corpus. Various researchers keep on working in these areas. However, in this research work, the relations between target entities (say: climate, population) along with the author’s stance and the country’s economic growth level are used to derive a statistical hypothesis. This hypothesis is being proved, discussed, and concluded as per the result obtained. All the missing country information for each Twitter account is filled up with a technique that uses meta information from tweets. A subset of the data is annotated with predefined seeding features, rules, and then applies the best performed supervised machine learning model to predict the remaining unlabeled tweets. Tweets are labeled as “believer” or “denier” for each country, and a hypothesis is being proved based on the statement made by rich and poor countries. The statistical result also shows that there exists a positive correlation between the GDP growth rate and the number of deniers and believers in each country. These techniques, experimental findings, and statistical analysis are presented in this paper.