Sentiment Analysis with Limited Training Data

Sentiments are positive and negative emotions, evaluations and stances. This dissertation focuses on learning based systems for automatic analysis of sentiments and comparisons in natural language text. The proposed approach consists of three contributions: 1. Bag-of-opinions model: For predicting document-level polarity and intensity, we proposed the bag-of-opinions model by modeling each document as a bag of sentiments, which can explore the syntactic structures of sentiment-bearing phrases for improved rating prediction of online reviews. 2. Multi-experts model: Due to the sparsity of manually-labeled training data, we designed the multi-experts model for sentence-level analysis of sentiment polarity and intensity by fully exploiting any available sentiment indicators, such as phrase-level predictors and sentence similarity measures. 3. LSSVMrae model: To understand the sentiments regarding entities, we proposed LSSVMrae model for extracting sentiments and comparisons of entities at both sentence and subsentential level. Different granularity of analysis leads to different model complexity, the finer the more complex. All proposed models aim to minimize the use of hand-labeled data by maximizing the use of the freely available resources. These models explore also different feature representations to capture the compositional semantics inherent in sentiment-bearing expressions. Our experimental results on real-world data showed that all models significantly outperform the state-of-the-art methods on the respective tasks