BrianMsane/Sentiment-Analysis-in-Swahili

Sentiment Analysis on a Swahili Dataset gathered from X (Twitter) # Sentiment-Analysis-in-Swahili ## Description Kiswahili is a lingua franca spoken by 100-150 million people across East Africa. It is an official language in the DRC, Kenya, Tanzania, and Uganda. On social media, Swahili speakers tend to express themselves in their own local dialect. This data can help you to analyze social conversations online and determine deeper context as they apply to a topic, brand or theme. Sentiment analysis relies on multiple word senses and cultural knowledge and can be influenced by age, gender and socio-economic status. For this task, we have collected annotated Swahili sentences from Twitter. The objective of this challenge is to classify whether a Swahili sentence is of positive, negative, or neutral sentiment. This is a multiclass task. Such solutions could be used by banking, insurance companies, or social media influencers to better understand and interpret a product’s audience and their reactions. ## Running Code Please use Google colab to run the code and on a T4 Runtime. Run all can be selected to automate cell running. The code gets the new version of accelerate and will require you to restart the runtime and run all the cells. The point will be indicated by the code breaking as you run all cells. The cells will run one after the other so the run all can be used to automate that. As the code runs new files will be created and used by the code. For the data, attach the necessary files. ## Reward This work was the third place winner for the Google NLP Hack Series: Swahili Social Media Sentiment Analysis Challenge hosted in zindi :)