| Summary: | Understanding “what others think” is one of the most eminent pieces of knowledge in the decision-making process required in a wide spectrum of applications. The procedure of obtaining knowledge from each aspect (property) of users' opinions is called aspect-based sentiment analysis which consists of three core sub-tasks: aspect extraction, aspect and opinion-words separation, and aspect-level polarity classification. Most successful approaches proposed in this area require a set of primary training or extensive linguistic resources, which makes them relatively costly and time consuming in different languages. To overcome the aforementioned challenges, we propose an unsupervised paradigm for aspect-based sentiment analysis, which is not only simple to use in different languages, but also holistically performs the subtasks for aspect-based sentiment analysis. Our methodology relies on three coarse-grained phases which are partitioned to manifold fine-grained operations. The first phase extracts the prior domain knowledge from dataset through selecting the preliminary polarity lexicon and aspect word sets, as representative of aspects. These two resources, as primitive knowledge, are assigned to an expectation-maximization algorithm to identify the probability of any word based on the aspect and sentiment. To determine the polarity of any aspect in the final phase, the document is firstly broken down to its constituting aspects and the probability of each aspect/polarity based on the document is calculated. To evaluate this method, two datasets in the English and Persian languages are used and the results are compared with various baselines. The experimental results show that the proposed method outperforms the baselines in terms of aspect, opinion-word extraction and aspect-level polarity classification.
|
|---|
