Abstract-In the past decade many opinion mining and sentiment classification studies have been carried out for opinions in English. However, the amount of work done for non-English text opinions is very limited. In this review, we investigate opinion mining and sentiment classification studies in three non-English languages to find the classification methods and the efficiency of each algorithm used in these methods. It is found that most of the research conducted for non-English has followed the methods used in the English language with only limited usage of language specific properties, such as morphological variations. The application domains seem to be restricted to particular fields and significantly less research has been conducted in cross domains.

Abstract-Opinion mining and sentiment analysis have become popular in linguistic resource rich languages. Opinions for such analysis are drawn from many forms of freely available online/ electronic sources, such as websites, blogs, news re-ports and product reviews. But attention received by less resourced languages is significantly less. This is because the success of any opinion mining algorithm depends on the availability of resources, such as special lexicon and WordNet type tools. In this research, we implemented a less complicated but an effective approach that could be used to classify comments in less resourced languages. We experimented the approach for use with Sinhala Language where no such opinion mining or sentiment analysis has been carried out until this day. Our algorithm gives significantly promising results for analyzing sentiments in Sinhala for the first time.

No abstract

No abstract

Space and time related data generated is becoming ever more voluminous, noisy and heterogeneous outpacing the research efforts in the domain of climate. Nevertheless, this data portrays recent climate/ weather change patterns. Thus, insightful approaches are required to overcome the challenges when handling the so called “big data” to unravel the recent unprecedented climate change in particular, its variability, frequency and effects on key crops. Contemporary climate-crop models developed at least two decades ago are found to be unsuitable for analysing complex climate/weather data retrospectively. In this context, the chapter looks at the use of scalable time series analysis, namely ARIMA (Autoregressive integrated moving average) models and data mining techniques to extract new knowledge on the climate change effects on Malaysia's oil palm yield at the regional and administrative divisional scales. The results reveal recent trends and patterns in climate change and its effects on oil palm yield impossible otherwise e.g. Traditional statistical methods alone.