Twitter Analyzer—How to Use Semantic Analysis to Retrieve an Atmospheric Image around Political Topics in Twitter

摘要

Social media are heavily used to shape political discussions. Thus, it is valuable for corporations and political parties to be able to analyze the content of those discussions. This is exemplified by the work of Cambridge Analytica, in support of the 2016 presidential campaign of Donald Trump. One of the most straightforward metrics is the sentiment of a message, whether it is considered as positive or negative. There are many commercial and/or closed-source tools available which make it possible to analyze social media data, including sentiment analysis (SA). However, to our knowledge, not many publicly available tools have been developed that allow for analyzing social media data and help researchers around the world to enter this quickly expanding field of study. In this paper, we provide a thorough description of implementing a tool that can be used for performing sentiment analysis on tweets. In an effort to underline the necessity for open tools and additional monitoring on the Twittersphere, we propose an implementation model based exclusively on publicly available open-source software. The resulting tool is capable of downloading Tweets in real-time based on hashtags or account names and stores the sentiment for replies to specific tweets. It is therefore capable of measuring the average reaction to one tweet by a person or a hashtag, which can be represented with graphs. Finally, we tested our open-source tool within a case study based on a data set of Twitter accounts and hashtags referring to the Syrian war, covering a short time window of one week in the spring of 2018. The results show that while high accuracy of commercial or other complicated tools may not be achieved, our proposed open source tool makes it possible to get a good overview of the overall replies to specific tweets, as well as a practical perception of tweets, related to specific hashtags, identifying them as positive or negative.