Sentiment analysis on the impact of online education on university students in Kenya using opinion data collected from students in different universities.

Many universities and learning institutions transitioned to online learning through adoption of video conferencing tools and e-learning platforms. This brought about several challenges on the students. Some institutions sent surveys to gain more information on how to improve the online delivery of education. It has been a challenge for schools to obtain proper outputs from their surveys.

Surveys are an important tool used to describe the characteristics of a population. Many learning institutions use surveys to obtain feedback from their students. Some institutions conducted a basic survey to collect feedback, but this can be challenging to analyze and draw conclusions from.

Emotion Analysis - the developed application features a custom emotion analysis algorithm. Sentiment Analysis - the developed application uses VADER – a lexicon-based and rule-based NLP sentiment analysis algorithm. The data was collected through a Google Form and saved in Google Sheets, and further into CSV files. Since the data collected was small, all the opinions were used in testing. Output was the sentiments, emotions, and the visualization of the outputs.

Hutto, C.J. & Gilbert, E.E. (2014). VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text. Eighth International Conference on Weblogs and Social Media (ICWSM-14). Ann Arbor, MI, June 2014. Link: https://pypi.org/project/vaderSentiment/