Search

Sentiment analysis has become a phenomenon with the proliferation of social media and the popularity of opinion-rich resources such as online reviews and blogs. Even though significant advances have been achieved in this field, there are still some major challenges to be addressed – i.e. sentiment analysis in multiple languages or thematic domains. Only a few studies have focused on minor or morphologically rich languages. Moreover, it is a question of whether the results of sentiment analysis could be further improved by incorporating the surrounding context (local or chronological) of the analyzed document. This paper presents a language- and domain-independent sentiment analysis model based on character n-grams which improves the classifiers performance by utilizing surrounding context. Four experiments on various datasets were conducted in order to validate the model. The datasets included a reference corpus containing movie reviews in English, movie reviews in the Czech language, the bestselling Amazon book of 2012 Fifty Shades of Grey novel reviews dataset from three Amazon language mutations (English, German, and French), another reference corpus containing Amazon reviews in multiple languages (German, French, and Japanese), and a multi-domain dataset (movies, books, and product categories ranging from electronics and home appliances to sports gear and supplies for hobbies and pets). The experiments confirmed the approach of incorporating the surrounding context in order to be effective for datasets from various languages and domains, suggesting a strong performance of a character n-gram based model for multi-domain and language datasets as well. A simple all-in-one classifier, which uses a mixture of labeled data from multiple languages (or domains) to train a sentiment classification model, may rival more sophisticated domain/language adaptation techniques. Such an approach reflects the needs of companies – with the interconnectedness of today's world, most companies operate across multiple markets and would find it difficult to obtain a specific sentiment analysis solution for each market they serve.

Sentiment lexicons including opinion words, sentiment phrases, and idioms with sentiment polarities play an important role in sentiment analysis tasks. Apart from explicit sentiment features, extracting implicit sentiment features is a challenging research issue. The sentiment expression is very domain-specific, and constructing a general sentiment lexicon that is suitable for all domains is hard or even impossible. In this paper, we propose a novel sentiment unit context propagation framework to extract Chinese microblog-specific explicit and implicit sentiment features. In the process of the selection of seed sentiment units, we select the seed sentiment units that have a large standard degree of centrality with other units, and mark these units with sentiment labels using general sentiment lexicons and manual calibrations. To realize sentiment label propagation from a small amount of labeled sentiment units to unlabeled ones, we exploit local contexts, topic features, and so`cial relationships among users in microblog social networks. After that, the sentiment scores of units are calculated using unit context sentiment propagation. Experiments on two real-world microblog data sets demonstrate that our method can generate microblog-specific sentiment lexicons effectively. Furthermore, the sentiment classification accuracies significantly outperform state-of-the-art baselines.

Part-of-speech (POS) tagging is a fundamental task in natural language processing (NLP). A robust POS tagger plays an important role in most NLP problems and applications, including syntactic parsing, semantic parsing, machine translation, and question answering. Although a lot of efficient POS taggers has been developed for general, conventional text, little work has been done for social media text. In this paper, we present an empirical study on POS tagging for Vietnamese social media text, which shows several challenges compared with tagging for general text. Social media text does not always conform to formal grammars and correct spelling. It also uses abbreviations, foreign words, and emoticons frequently. A POS tagger developed for conventional text would perform poorly on such noisy data. We address this problem by proposing a tagging model based on Conditional Random Fields (CRFs) with various kinds of features for Vietnamese social media text. We also investigate the effect of features extracted from word clusters under the Brown and canonical correlation analysis (CCA) based clustering in semi-supervised settings. We introduce an annotated corpus for POS tagging, which consists of more than four thousand sentences from Facebook, the most popular social network in Vietnam. Using this corpus, we performed a series of experiments to evaluate the proposed model. Our model achieved 88.26% and 88.92% tagging accuracy in supervised and semi-supervised scenarios, respectively, which are nearly 12% improvement over vnTagger, a state-of-the-art and most widely used Vietnamese POS tagger developed for general, conventional text. In addition, the semi-supervised model outperformed, in terms of accuracy, the version of vnTagger trained on the same Facebook dataset, showing the usefulness of word cluster features. 1