SentiHealth-Cancer: A sentiment analysis tool to help detecting moodof patients in online social networks

Abstract—Abstract Cancer is a critical disease that affects millions of people and families around the world. In2012 about 14.1 million new cases of cancer occurred globally. Because of many reasons like the severityof some cases, the side effects of some treatments and death of other patients, cancer patients tend to beaffected by serious emotional disorders, like depression, for instance. Thus, monitoring the mood of thepatients is an important part of their treatment. Many cancer patients are users of online social networksand many of them take part in cancer virtual communities where they exchange messages commentingabout their treatment or giving support to other patients in the community. Most of these communitiesare of public access and thus are useful sources of information about the mood of patients. Based on that,Sentiment Analysis methods can be useful to automatically detect positive or negative mood of cancerpatients by analyzing their messages in these online communities.Objective: The objective of this work is to present a Sentiment Analysis tool, named SentiHealth-Cancer(SHC-pt), that improves the detection of emotional state of patients in Brazilian online cancer commu-nities, by inspecting their posts written in Portuguese language. The SHC-pt is a sentiment analysis toolwhich is tailored specifically to detect positive, negative or neutral messages of patients in online com-munities of cancer patients. We conducted a comparative study of the proposed method with a set ofgeneral-purpose sentiment analysis tools adapted to this context.Methods: Different collections of posts were obtained from two cancer communities in Facebook. Addi-tionally, the posts were analyzed by sentiment analysis tools that support the Portuguese language(Semantria and SentiStrength) and by the tool SHC-pt, developed based on the method proposed inthis paper called SentiHealth. Moreover, as a second alternative to analyze the texts in Portuguese, thecollected texts were automatically translated into English, and submitted to sentiment analysis toolsthat do not support the Portuguese language (AlchemyAPI and Textalytics) and also to Semantria andSentiStrength, using the English option of these tools. Six experiments were conducted with some varia-tions and different origins of the collected posts. The results were measured using the following metrics:precision, recall, F1-measure and accuracy.