SENTIMENT ANALYSIS USING NAIVE BAYES WITH BIGRAMS
Published In: INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING AND INFORMATION TECHNOLOGY
Author(s): ADNAN RASHID HUSSAIN , MOHD ABDUL HAMEED , S. FOUZIA SAYEEDUNNISSA
Abstract: With the rapid growth of reviews, ratings, recommendations and other forms of online expression, online opinion has turned into a kind of virtual currency for businesses looking to market their products, identify new opportunities and manage their reputations. Sentiment analysis extracts, identifies and measures the sentiment or opinion of documents as well as the topics within these documents. The Naïve Bayes algorithm performs a boolean classification i.e. it classifies a document as either positive or negative according to its sentiment. We have already seen by Sayeedunnisa et al [1], that the application of Naïve Bayes trained on high value features, extracted from a bag-of-words model, yields an accuracy of 89.2%. This paper studies the application of Naïve Bayes technique for sentiment analysis by including training of bigram features to improve accuracy and the overall performance of the classifier. We also evaluate the impact of selecting low vs. high value features, calculated
- Publication Date: 05-Jan-2014
- DOI: 10.15224/978-981-07-8859-9-61
- Views: 0
- Downloads: 0
RAPID VISUAL SCREENING METHOD FOR SEISMIC VULNERABILITY ASSESSMENT OF EXISTING BUILDINGS IN BUKIT TINGGI, PAHANG, MALAYSIA
Published In: INTERNATIONAL CONFERENCE ON ADVANCES IN CIVIL, STRUCTURAL AND MECHANICAL ENGINEERING
Author(s): M. ALEL , M. GHAFAR , N. RAMLY
Abstract: Bukit Tinggi may experience low earthquake hazard but are still at high risk of substantial damage and loss. Dense concentration of buildings and infrastructure in some areas mainly due to the hospitality industry can generate this high risk level. This study is focused on identify, inventory and rank buildings in Bukit Tinggi to assess seismic vulnerability buildings. The methodology is based on the rapid visual screening (RVS) procedure. Major parameters that have effects on the building score are primary structural lateral-load-resisting system, construction material, and other seismic related characteristic such as soiltype and building irregularity. Building with higher S scores corresponding to better seismic performance. Most of the buildings in Bukit Tinggi are less seismic risk 74% while another 26% considered in need of further evaluation.
- Publication Date: 05-Jan-2014
- DOI: 10.15224/978-981-07-8859-9-27
- Views: 0
- Downloads: 0