Evolving dictionary based sentiment scoring framework for patient authored text

In recent days, the Government and other organizations are focusing on providing better health care to people. Understanding the patients experience of care-received is key for providing better health care. With prevailing usage of social media applications, patients are expressing their experience over social media. This patient authored text is a free-unstructured data which is available over social media in large chunks. To extract the sentiments from this huge data, a domain-specific dictionary is required to get better accuracy. The proposed approach defines a new domain-specific dictionary and uses this in sentiment scoring to enhance the overall sentiment classification on patient authored text. We conducted experiments on the proposed approach using NHS Choices dataset and compared it with popular classifiers like linear regression, stochastic gradient descent, dictionary-based approaches: VADER and AFINN. The results prove that the proposed approach is an effective strategy for sentiment analysis over patient authored text which helps in improving the classification accuracy.