Recommendation as classification: using social and content-based information in recommendation
AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
Item-based collaborative filtering recommendation algorithms
Proceedings of the 10th international conference on World Wide Web
Compound Classification Models for Recommender Systems
ICDM '05 Proceedings of the Fifth IEEE International Conference on Data Mining
Top 10 algorithms in data mining
Knowledge and Information Systems
Why we twitter: understanding microblogging usage and communities
Proceedings of the 9th WebKDD and 1st SNA-KDD 2007 workshop on Web mining and social network analysis
Supervised Machine Learning: A Review of Classification Techniques
Proceedings of the 2007 conference on Emerging Artificial Intelligence Applications in Computer Engineering: Real Word AI Systems with Applications in eHealth, HCI, Information Retrieval and Pervasive Technologies
Collaborative filtering recommender systems
The adaptive web
Ecosystems Monitoring: An Information Extraction and Event Processing Scientific Workflow
SERVICES '10 Proceedings of the 2010 6th World Congress on Services
Mahout in Action
| Hi-index | 0.00 |
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.