Emma Raducanu

Context I collect recent tweets about Emma Raducanu, winner of women US Open 2021. The teen Brit with Romanian and Chinese parents, born in Canada and arrived in Great Britain at 2 years old, stormed the US event from qualifiers, playing 10 games without losing one single set (20 sets won in a row). She is the first British woman to win a Grand Slam since 1977 (Virginia Wade), the first women in US Open history to win the event from the qualifiers. She jumped more than 120 points in the ranking to land on 23rd position. She is also a very good student, landing A grades in mathematics and economy (her preferred domains) in her selective grammar school from south London.

Data collection The data is collected using tweepy Python package to access Twitter API. I use a relevant search term for the topic (#EmmaRaducanu).

Data collection frequency The data is collected continuously using a script that collects a small number of recent tweets (using Twitter API and tweepy). The dataset obtained at each sampling time step is merged with current (or previously collected) dataset and stored dataset in csv format is saved on disk. Once or several times per day the currently accumulated dataset is uploaded on Kaggle as a new version of the tweets dataset.

Inspiration You can perform multiple operations on the tweets about this British teen with meteoric ascension at US Open 2021. Here are few possible suggestions:

Study the subjects of recent tweets about the new US Open champion or about tennis; Perform various NLP tasks on this data source (topic modelling, sentiment analysis); Can you identify tweets about tennis women, British athletes or US Open? Follow the trends in the news about tennis, US Open or Emma; Perform sentiment analysis on the tweets corpus but also split on topics, countries etc. Study the hashtags (associated to the tweets) distribution.

CC0

Original Data Source: Emma Raducanu