This document discusses using a semi-supervised learning approach with a transductive support vector machine (TSVM) model for sentiment analysis of blogs relating to organized crime in Mexico. It gathered data from a controversial blog about the drug trade, cleaned the text, labeled some instances, and trained a TSVM model. A 10-fold cross validation experiment showed the TSVM achieved higher accuracy than a standard SVM. While the TSVM was slower, its accuracy was promising, especially with fewer labeled instances. Future work could involve subjectivity classification before polarity and addressing errors in the current approach.