Search

The advancement of internet technology and machine learning techniques in information retrieval make Sentiment mining or analysis become popular among researchers. There are many sentiment analysis researches that have been done on English text using various machine learning techniques. However, there are very limited researches on Malay text sentiment analysis. This research focuses on preprocessing techniques for stemming Malay text namely Reverse Porter Algorithm (RPA) and Backward- Forward Algorithm (BFA) and Artificial Immune Network (AIN) for extracting sentiment from Malay newspaper articles. Data representation is also important where the data must be converted into suitable form for Artificial Immune Network Algorithm to work. To represent the data, vector space representation is used with three parameters represent the actual word, the frequency of occurrence of the word in a particular sentence and the polarity of the sentences. Lastly, the sentiment analysis algorithm was developed using immune network from Artificial Immune System (AIS). The result from stemming the Malay text using new reverse Porter algorithm shows some improvement in processing time compared to backward-forward algorithm. However, the sentiment analysis accuracy using AIN with both stemming techniques show almost similar result. In the future, thorough study on artificial immune system techniques and comparative study on other machine learning techniques for sentiment analysis is required for better result. [ABSTRACT FROM AUTHOR]

Opinions about a particular product, service or person are communicated effectively through online media such as Facebook, MySpace and Twitter. Unfortunately only a few researchers had researched on the performance of opinion mining using online messages that were written in Malay Languages. Opinion mining processing that uses Natural Language Processing approach is difficult due to the high content of noisy texts in online messages. On the other hand, opinion mining that uses machine learning approach requires a good feature selection technique since the current filter typed feature selection techniques require interference from the user to select the appropriate features. This study used a feature selection technique based on artificial immune system to select the appropriated features for opinion mining. Experiments with 2000 online movie reviews illustrated that the technique has reduced 90% of the features and improved opinion mining accuracy up to 15% with k Nearest Neighbor classifier and up to 6% with Naïve Baiyes classifier. [ABSTRACT FROM AUTHOR]

There are sheer volume of rich web resources such as digital newspaper, e-forum, blogs, Facebook and Twitter. Mining the digital text resources may reveal interesting knowledge to respective individuals or organizations. Text mining and sentiment mining or analysis are parts of a new area in sentiment research. Sentiment mining for Malay Newspaper (SAMNews) is constructed based on the artificial immune system called negative selection algorithm which is able to classify the sentiment in newspaper's sentences into the polarity (positive, negative or neutral) intelligently. The sentiment analysis in this project utilized 1000 sentences from newspapers to evaluate the average accuracy. The research used 900 sentences from newspapers as the training data and another 100 as the testing data. The accuracy is achieved at 88.5%. In the future, a comparative study on Artificial Immune System and other techniques or algorithms can be carried out to enhance the performance of the sentiment classification model. [ABSTRACT FROM AUTHOR]

More and more Web based systems are being developed by composing other single or even composite services. This is due to the fact that not all available services are able to satisfy the needs of a user. The process of composing Web services involves discovering the appropriate services, selecting the best services, combining those services together, and finally executing them. Although much research efforts have been dedicated to the discovery, selection, and composition of services, the process of testing the Web service composition has not been given the same attention. This paper discusses the importance of Web services composition testing, provides a classification of the most prominent approaches in that area, presents several criteria for comparison of those approaches, and conducts a comparative evaluation of the approaches. The results of the paper give an essential perspective to do research work on Web services composition testing. [ABSTRACT FROM AUTHOR]