Analyzing the Sentiment of MOOC Discussion Posts

he purpose of the project is to identify common difficulties that learners may face and to understand their emotions as they progress through Massive Open Online Course (MOOC). The research involves data from ten different courses from Coursera. Pieces of text that students have made are extracted and sent to Google Cloud Natural Language API, which performs a sentiment analysis of a text. The main goal is to assist instructors with monitoring MOOC to make it more efficient and facilitate students progress. To achieve this, the first step was to gather all the data from each of the courses. Programming was used to dump all that data into one big database. The program used here is called Pycharm and it is required the use of python and sql to be able to create the database. Once the database is created, using coding only the pieces of information that are needed are selected. Extracted data (texts) should be where students make comments or ask questions. Next, the data is queried and sent to Google Cloud Natural Language API, which breaks down all the sentences to individual words. Next, the program categorize and sort each word according to its connotation e.g. positive, negative or neutral. The overall sentiment depends on the emotion that had the highest number. If positives and negatives are all balanced out then the sentiment is neutral. Sentiment scores range from -1 to 1, where -1 is the most negative, 1 is the most positive and anywhere near 0 is neutral. Positive sentiment scores indicate that students are doing well on their course, while neutral sentiment scores indicate that course is balanced out with difficulties and easy tasks. However, negative sentiment is the most important to instructors since it indicates that students are struggling with the course and the course needs improvement.