The spread of the Pneumonia Coronavirus Disease 2019 (COVID-19) or Corona virus has affected several industrial sectors in Indonesia, particularly in the tourism and economy sector. Corona virus has been declared by the World Health Organization (WHO) as a pandemic that has spread to various parts of the world including Indonesia. In this regard, the Government of the Republic of Indonesia then declared the Corona virus as a non-natural national disaster. The Case Fatality Rate (CFR) of the Corona virus is 8.37%, placing Indonesia as one of the countries with the highest mortality ratio in the world. Currently, the Government of Indonesia has not implemented a lockdown policy, but there are some people who deplore the government's firmness in imposing the policy and there are also those who support the government for not making the lockdown status decision. Therefore, the lockdown is still a debate in the public. This can be read on social media Twitter, where many people express their opinions about the lockdown policy in Indonesia. Based on this polemic, this research has obtained a classification model that can differentiate between pro and contra tweets on the lockdown policy topics using Indonesian tweets. By using the Bernoulli NB algorithm as a classification model, an optimal value with the highest f-measure score of 88,57% was obtained. This model can be used to assess the effectiveness of communication in implementing lockdown policy to slow the spread of COVID-19 because it can identify public opinion about the trends in supporting or rejecting the lockdown policy.
|Number of pages||9|
|Journal||Journal of Theoretical and Applied Information Technology|
|Publication status||Published - 31 Jul 2021|
- Sentiment Analysis
- Supervised Learning
- Text Classification