opinion mining and sentiment analysis
- Supervised
- Unsupervised
- Semi-supervised
- Methods:k-NN, NB, ME, SVM
- Terms: frequency, tf/idf, cosine distance, similarity
- Supervised NB approach: http://karpathy.ca/mlsite/lecture2.php
- Supervised kNN approach: http://karpathy.ca/mlsite/lecture3.php
- Full comprehensive NLTK site: http://streamhacker.com/
- Twitter, discovering customer insight: http://www.jucs.org/jucs_18_8/discovering_consumer_insight_from/jucs_18_08_0973_0992_chamlertwat.pdf
- Good starting: http://andybromberg.com/sentiment-analysis-python/?utm_source=Python+Weekly+Newsletter&utm_campaign=c15c89a350-Python_Weekly_Issue_75_February_21_2013&utm_medium=email
- Twitter, handson SA: http://ravikiranj.net/drupal/201205/code/machine-learning/how-build-twitter-sentiment-analyzer
- Will it Python, Machine Learning for hackers: http://slendrmeans.wordpress.com/will-it-python/