Custom-built Bulgarian language data sets, used by АзБуки.ML for sentiment analysis, text classification, summarisation and generation. Open-source & free to use in any ML project.
in this project, I have wanted to know the happiest country around the world, by created visualizations to reveal insights from a World Happiness Report 2020 data set and create data visualizations that tell a story or highlight patterns in the data set.
The following is a research paper with the hypothesis to study whether teenage development can also be observed via their twitter tweets. Using a dataset of teenagers from twitter I was able to confirm my study that as we develop as humans our development is also found on our social media via linguistic aspects such as spelling, maturity, bad wo…