Search results

This paper purposed a multi-facet sentiment analysis system.

Hence, This paper uses multidomain resources to build a sentiment analysis system. The manual lexicon based features that are extracted from the resources are fed into a machine learning classifier to compare their performance afterward. The manual lexicon is replaced with a custom BOW to deal with its time consuming construction. To help the system run faster and make the model interpretable, this will be performed by employing different existing and custom approaches such as term occurrence, information gain, principal component analysis, semantic clustering, and POS tagging filters.

The proposed system featured by lexicon extraction automation and characteristics size optimization proved its efficiency when applied to multidomain and benchmark datasets by reaching 93.59% accuracy which makes it competitive to the state-of-the-art systems.

The construction of a custom BOW. Optimizing features based on existing and custom feature selection and clustering approaches.

This paper examines the financial ratios that may have a significant effect on the efficiency in Malaysian listed companies. Nine financial ratios measure seven variables which are firm visibility, tangibility, working capital, leverage, liquidity, productivity and profitability.

Data are collected from 108 public listed companies in Malaysia. The data extracted from companies' annual reports for three years 2012–2014. STATA software analysis is used to examine these relationships.

The results show each of tangibility and liquidity have negative relationships with efficiency ratio. In against of that, profitability, working capital and productively positively link to efficiency. Leverage which is measured by two ratios – Debt ratio and Debt equity ratio – shows mix results. Debt ratio shows a positive but not significant relationship with efficiency ratio and Debt equity ratio shows a negative significant relationship with efficiency ratio.

The results benefit companies, investors, economists and governments regulators in Malaysia-to understand the efficiency determinants, so help to make the right decision to enhance the efficiency level in companies which leads to enhance the amount of investments which in turn, enhance the country's economy in general.

This study differs than previous studies number of aspects: first the study covers a three years' period between 2012 and 2014, this period presents the movement of Malaysian current into depreciation with more than 45 percent of its value. Second, in the Malaysia context, this study examines new variables such as firm visibility, tangibility, and productivity. Third, the results of this study will help managers, shareholders, investors, regulators and other parties to make right decisions that will enhance the level of firm efficiency which enhances the investments and the economy of Malaysia.

This study aimed to determine mothers' knowledge of children with congenital heart disease (CHD) and to examine the relationship between types of CHD, the duration of treatments, the perception of the severity of illness and the mothers' knowledge.

A correlation study was conducted among 84 mothers of children (from infancy to six years old) with CHD who had attended pediatric cardiology clinics and pediatric units in three tertiary hospitals in Bangkok, Thailand. The two questionnaires aimed to evaluate the mothers' knowledge and perceptions of the severity of illness. Descriptive statistics, Spearman's rank-order correlation and Fisher's exact test were used to analyze the data.

Knowledge levels of mothers of children with CHD were at a high level with a mean score of 34.79 (SD = 8.23), but the knowledge domain of preventing complications was at a low level with a mean score of 14.95 (SD = 5.28). The types of CHD and the perceptions of illness were not correlated with the mothers' knowledge, but the duration of treatments was significantly correlated (r = 0.271, p < 0.05).

Healthcare professionals, especially nurses, should emphasize proper health education on complication prevention and the duration of treatments for children. Moreover, mothers should be supported to nurture children with CHD to reduce possible complications and prepare for cardiac surgery where needed.

The study examines the association between trade (exports and imports), foreign direct investment (FDI) and economic growth in the Bay of Bengal Initiative for Multi-Sectoral Technical and Economic Cooperation (BIMSTEC) countries using data from 1991 to 2019.

Augmented Dickey–Fuller (ADF) and Phillips–Perron (PP) unit root tests were applied to check the stationary of the data while the Johansen cointegration test and Vector Error Correction Model (VECM) was used to analyze long-run and short-run relationships.

The results indicate a long-run relationship between trade, FDI and economic growth in all selected countries except Bhutan. Additionally, a bidirectional causality exists between gross domestic product (GDP) and FDI in India, Bangladesh, Myanmar, Nepal, Bhutan and Sri Lanka, while unidirectional causality from GDP to FDI is observed in Thailand. Moreover, a one-way causality from exports to GDP exists in Bangladesh, Nepal, Bhutan, Sri Lanka and Myanmar, whereas a bidirectional relationship exists in India and Thailand.

This paper will be highly beneficial for regulators and policymakers in the designated economies, aiding in the formulation of FDI and trade policies that promote economic progress and development.

Most previous studies examining the relationship between macroeconomic variables have focused on developed nations. This study is the first to explore the relationship between trade (exports and imports), FDI and economic growth in the BIMSTEC countries.

Plant cultivation holds a pivotal role in agriculture, necessitating precise disease identification for the overall health of plants. This research conducts a comprehensive comparative analysis between two prominent deep learning algorithms, convolutional neural network (CNN) and DenseNet121, with the goal of enhancing disease identification in tomato plant leaves.

The dataset employed in this investigation is a fusion of primary data and publicly available data, covering 13 distinct disease labels and a total of 18,815 images for model training. The data pre-processing workflow prioritized activities such as normalizing pixel dimensions, implementing data augmentation and achieving dataset balance, which were subsequently followed by the modeling and testing phases.

Experimental findings elucidated the superior performance of the DenseNet121 model over the CNN model in disease classification on tomato leaves. The DenseNet121 model attained a training accuracy of 98.27%, a validation accuracy of 87.47% and average recall, precision and F1-score metrics of 87, 88 and 87%, respectively. The ultimate aim was to implement the optimal classifier for a mobile application, namely Tanamin.id, and, therefore, DenseNet121 was the preferred choice.

The integration of private and public data significantly contributes to determining the optimal method. The CNN method achieves a training accuracy of 90.41% and a validation accuracy of 83.33%, whereas the DenseNet121 method excels with a training accuracy of 98.27% and a validation accuracy of 87.47%. The DenseNet121 architecture, comprising 121 layers, a global average pooling (GAP) layer and a dropout layer, showcases its effectiveness. Leveraging categorical_crossentropy as the loss function and utilizing the stochastic gradien descent (SGD) Optimizer with a learning rate of 0.001 guides the course of the training process. The experimental results unequivocally demonstrate the superior performance of DenseNet121 over CNN.