by on with 1 Comment

Pitch 1

Social media sentiments to predict mental health of people during the stages of pandemic in the United States

  1. I think it is important to know how people are feeling, whether they are hopeful, devastated, excited, or feeling fine during the pandemic.
  2. With new variants showing up, people’s sentiments may keep changing. So, I want to see if virus variants, mask mandates loosening up, or vaccine rollout had an impact on people’s sentiments. For example, people were probably being hopeful and excited after getting vaccinated but the delta variant may have increased the negative sentiments.
  3. I plan to use Twitter data with a sentiment analysis machining learning model and then visualizing the data with interactive charts
  4. I will be using Twitter’s API code and collect the tweets with #covid19, #pandemic, and other covid related hashtags (#).
  5. Timeline of the covid-19 event (From the timeline below I will only pick certain events): https://www.ajmc.com/view/a-timeline-of-covid19-developments-in-2020
  6. Resources: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3572023.

Pitch 2

Social media sentiments to predict the covid situation and vaccine rollout in different countries

  1. Why is this important?
    • ●  In the US people may be more hopeful and excited since the vaccination rate is going up and mask mandates are getting removed.
    • ●  However, there are parts of the world where the majority of the population is not vaccinated, and a lot of people are dying of covid.
    • ●  So, it would be interesting to predict the parts of the world with higher vaccination rates and better situations and parts of the world with lower vaccination rates and worse situations through Twitter sentiments.
  2. I plan to use Twitter data with a sentiment analysis machining learning model and then visualizing the data with interactive charts
  3. I will be using Twitter’s API code and collect the tweets with #covid19, #pandemic, and other covid related hashtags (#) and categorize these according to country names.
  4. I might cherry-pick 5-6 countries only.
  5. Resources: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3572023
Pitch 3

Predicting the tourist volume and touristic behavior with search engine data

  1. To be able to predict the volume of tourists arriving at a certain destination is important in order to plan and make available adjustments according to the demand.
  2. Especially during this global pandemic, it is very helpful to know the volume of the tourist arriving at the destination so that there can be proper and enough arrangements for testing, quarantining, and knowing whether the area is going to become a high risk for covid.
  3. I will be using google trends data, and use keywords related to tourism to predict the volume of tourists.
  4. I will be doing this for only 5 countries.
  5. To see if my predictions are correct I will test them with available data from the past.
  6. Data for tourism volume -> https://ourworldindata.org/tourism https://www.statista.com/statistics/261733/countries-in-asia-pacific-region-ranked-by-internationa l-tourist-arrivals/

Resources:https://www.sciencedirect.com/science/article/abs/pii/S2211973617300570