... impor-tant, and presentspreliminary experimentswith training data labeled with emoticons,which has the potential of being indepen-dent of domain, topic and time.1 IntroductionRecent years have ... 2,000 to 22,000 in increments of 1,000, an equal numberbeing taken from the positive and negative sets) asoptimising training data. For each set of trainingdata we extracted a context of an increasing ... increasing num-ber of tokens (from 10 to 1,000 in increments of 10)both before and in a window4around the smile orfrown emoticon. The models were trained using thisextracted context and tested...