| Popis: |
We introduce our initial work for developing a social networks recommender system called T-Recs. The system is a time-aware Twitter-based alternative medicine recommender system. We collected a set of tweets (around 500,000 tweets) that contain specific hash tags (#throwing up, #headache, #itching etc) for a three consecutive weeks. The individual tweets were examined manually by a domain expert (a medical doctor) who inspected the tweet sentiments along with the tweet's timestamp. Using this data, the domain expert assigned a preliminary label to the tweet/group of tweets. We then trained a classifier using the hash tags and its labels taking into consideration other factors (i.e., age, gender, co-morbidity conditions) that the Tweeter must provide by taking a questionnaire. After the questions are answered, the recommender system makes recommendations based on the Tweet contents and the questionnaire factors for never-seen-before tweets. The classifier, is the core component of the recommender system, is designed as a Decision Tree algorithm to classify the Tweets. Each recommendation is made by the system provides a medical advice to promote public health awareness, and a link to the recommender systems' web portal to answer the questionnaire. When the questionnaire is submitted, the symptoms and Tweeter's basic information are consolidated and a recommendation is made available to the user at once. For the sake of feasibility, we only considered tweets that are sent from within the United States. |
