Machine Learning applications in elections. Sentimental analysis of tweets during campaigns
Session
Computer Science and Communication Engineering
Description
Machine Learning is one of the most impactful technology of our era. Increasingly powerful computers harnessed to algorithms refined over the past decade are driving an explosion of applications in everything from medical physics to materials. In this paper we are going to present how to use machine learning to analyse election campaigns. Our focus is on using natural language processing, especially sentimental analysis and text classification to analyse public posts of running candidates. As a case study, we will use a dataset of public tweets written in the English language, by a group of selected politicians. We will classify these tweets in three categories: Positive, Neutral and Negative by using classification algorithms. Since we are experiencing government elections in our country we will analyse how the sentiment of tweets by candidates is changing before and after elections. We will also analyse the correlation between the sentiments of tweets with the reaction they get from social media. The purpose of the presentation is to encourage social scientists to start using machine learning as an important tool for analysing election campaigns and their impact on public presentation of politicians.
Keywords:
machine learning, sentimental analysis, elections
Session Chair
Bertan Karahoda
Session Co-Chair
Krenare Pireva
Proceedings Editor
Edmond Hajrizi
ISBN
978-9951-550-19-2
Location
Pristina, Kosovo
Start Date
26-10-2019 1:30 PM
End Date
26-10-2019 3:00 PM
DOI
10.33107/ubt-ic.2019.266
Recommended Citation
Morina, Vesa and Shehu, Hakan, "Machine Learning applications in elections. Sentimental analysis of tweets during campaigns" (2019). UBT International Conference. 266.
https://knowledgecenter.ubt-uni.net/conference/2019/events/266
Machine Learning applications in elections. Sentimental analysis of tweets during campaigns
Pristina, Kosovo
Machine Learning is one of the most impactful technology of our era. Increasingly powerful computers harnessed to algorithms refined over the past decade are driving an explosion of applications in everything from medical physics to materials. In this paper we are going to present how to use machine learning to analyse election campaigns. Our focus is on using natural language processing, especially sentimental analysis and text classification to analyse public posts of running candidates. As a case study, we will use a dataset of public tweets written in the English language, by a group of selected politicians. We will classify these tweets in three categories: Positive, Neutral and Negative by using classification algorithms. Since we are experiencing government elections in our country we will analyse how the sentiment of tweets by candidates is changing before and after elections. We will also analyse the correlation between the sentiments of tweets with the reaction they get from social media. The purpose of the presentation is to encourage social scientists to start using machine learning as an important tool for analysing election campaigns and their impact on public presentation of politicians.