The soaring of diabetes cases in Malaysia has resulted in the appearance of diabetic retinopathy among diabetic patients. Diabetic retinopathy is a chronic eye disease triggered by diabetes, which could worsen eyesight functions and even blindness. Even though the cases were found to be common, medical experts still diagnose the disease manually, which increase the risk of incorrect diagnosis. To overcome this, the preliminary study on severity levels classifications of diabetic retinopathy from fundus images has been conducted by applying a deep learning model. A Convolutional Neural Network (CNN) deep learning model architecture is used to train the dataset, which is DenseNet. Various image pre-processing techniques have been applied to enhance the trained images. Moreover, data augmentation and test-time augmentation (TTA) are implemented in evaluating the training results and lower the overfitting, respectively. Prediction evaluation on the images and the effects of data augmentation and TTA by observing the quadratic weighted kappa values were conducted. Ultimately, a prediction model that is to predict and classify the severity labels of fundus images was developed. The prediction model achieved the quadratic weighted kappa score of 0.9308, with the accuracy of 65% on the Messidor-2 dataset, which were moderately accurate.
A rapid development of E-Commerce platforms has allowed retailers to introduce online product recommendations to persuade consumers purchase decisions. Recommendations system in E-Commerce can be implemented through development of opinion review or feedback system. The visibility of opinion review as a persuasive communication tool in recommendation context has been proven as an important role in purchasing process, which then triggers much attention recently among research scholars. To expand the current discussion on persuasive potential of online review system, this paper aims to explore how the quality of text message may affects the persuasiveness of online recommendation. A concept-level approach will be used in analyzing text readability ease towards generating persuasive communication message. A theoretical model is proposed to measure the effect of review length based on number of concept review towards opinion review readership and its persuasive features. In order to validate the model, we applied basic readability measure of Gunning-Fox Index (FOG) to examine readability ease of opinion review to a dataset containing 1054 reviews extracted from Amazon.com product review. The interrelationship between concept-level analysis, review readership and its persuasive review is further discussed in this paper.
In e-Commerce field, there are many researchers conducted on different properties of trust but lack of attention has been given to interpersonal based trust. This has lead to limitations for e-Commerce growth where social events have not yet fully duplicate into digital form especially in e-Commerce environment. Taking the advantage of rapid growth of social network nowadays, the objective of this study is to improve current e-Commerce implementation through social presence. In order to achieve this objective, this study has explored e-Commerce trust properties with its attributes as suggested by previous researchers. Trust factors based on social presence attributes also have been identified. This research hopes to provide a guideline to online businesses in order to develop a trusted website based on updated trend of e- Commerce which is more customer-oriented.
The viral nature the content of the Web has transformed the landscape of e-Commerce review platforms to be in a state of constant growth. Similarly, the prominent features of these platforms have been recognized to be among the dominant factors in shaping online consumer behavior. Nonetheless, in this regard, if the review platform returns too many reviews, and the reviews are presented in non-relevant manner, in which this may be cumbersome and time-consuming for consumers. Therefore, identifying credible reviews that contain valuable information has becomes increasingly important for online businesses. The main research question to be addressed in this study is to determine on how can a model be developed to improve the argument quality perceptions in the adoption of online reviews across e-Commerce review platform. Subsequently, the main objective to be achieved is to develop a model of argument quality for review’s adoption in the e-Commerce review platform. The potential effects of consumer relevance judgment from information retrieval perspective have been considered, which include perceived informative and affective relevance in developing the research model by using Elaboration Likelihood Model (ELM). A quantitative research method has been applied to test and validate the propose research model. The response data from 238 valid respondents was analyzed using the Partial Least Square Structural Modelling (PLS-SEM) technique. The findings from the results indicate that content novelty, content topicality, content similarity, content tangibility and content sentimentality could positively influence the perception of argument quality which lead to information adoption behavior. Finally, the importance of information relevancy was also highlighted in this study, which reveals some appropriate features that can be utilized by e-Commerce practitioners to better refine their information search criteria in the online review platforms.
Intention to purchase in existing online business practice is learned through observation of information display by online seller. The emergent growth of persuasive technologies currently holds a great potential in driving a positive influence towards consumer purchase behavior. But to date, there is still limited research on implementing persuasion concept into the recommender system context. Drawing upon the principle design of persuasive system, the main purpose of this study is to explore social learning advantages in creating persuasive features for E-Commerce recommender system. Based on Social Cognitive Theory, the influence of personal and environmental factors will be examined in measuring consumer purchase intention. In addition, dimensions of social learning environment are represented by observational learning theory and cognitive learning theory. From those reviews, this study assumed that social learning environment can be created based on attentiveness, retentiveness, motivational, knowledge awareness and interest evaluation cues of consumer learning factors. Furthermore, the persuasive environment of recommender system is assumed to have positive influence towards individual characteristics such as self-efficacy behavior, perceived task complexity and confused by over choice. Findings from those reviews have contributed to the development of a research model in visualizing social learning environment that can be used to develop a persuasive recommender system in E-Commerce and hence measures the impact towards consumer purchase intention.
'/%3e%3cuse xlink:href='%23a' transform='translate(0 -400)'/%3e%3cuse xlink:href='%23a' transform='translate(0 -600)'/%3e%3cuse xlink:href='%23a' transform='translate(0 -800)'/%3e%3cuse xlink:href='%23a' transform='translate(0 -1000)'/%3e%3cuse xlink:href='%23a' transform='translate(0 -1200)'/%3e%3cpath d='M0 0h1400v800H0z' style='fill:%23010066'/%3e%3cpath d='M576 100c-166.146 0-301 134.406-301 300s134.854 300 301 300c60.027 0 115.955-17.564 162.927-47.783-27.353 9.44-56.71 14.602-87.271 14.602-147.327 0-266.897-119.172-266.897-266.01 0-146.837 119.57-266.01 266.897-266.01 32.558 0 63.746 5.815 92.602 16.468C696.217 118.91 638.305 100 576 100z' style='fill:%23fc0'/%3e%3cpath d='m914.286 471.429-99.538-53.25 29.43 108.982-66.575-91.165-20.77 110.96-20.428-111.024-66.857 90.96L699.314 418l-99.701 52.943 74.065-85.192-112.8 4.441 103.694-44.62-103.555-44.94L673.8 305.42 600 220l99.538 53.25-29.43-108.982 66.575 91.165 20.77-110.96 20.428 111.023 66.857-90.959L814.97 273.43l99.702-52.944-74.065 85.193 112.8-4.441-103.694 44.62 103.555 44.94-112.785-4.79z' style='fill:%23fc0' transform='matrix(1.2738 0 0 1.2423 -89.443 -29.478)'/%3e%3c/svg%3e)
'/%3e%3cpath d='M200 752.362h200v300H200z' style='fill:%23fff;fill-opacity:1;stroke:none' transform='translate(0 -752.362)'/%3e%3cpath d='M400 752.362h200v300H400z' style='fill:%23ff883e;fill-opacity:1;stroke:none' transform='translate(0 -752.362)'/%3e%3c/svg%3e)
'%3e%3ccircle r='9'/%3e%3cg id='d'%3e%3cg id='c'%3e%3cg id='b'%3e%3cpath d='m-19 0 1.169 1.169L0 0l-17.831-1.169z'/%3e%3cpath id='a' d='m-.884.116.05.05L0 0z' transform='scale(19.2381)'/%3e%3cuse xlink:href='%23a' transform='scale(1 -1)'/%3e%3c/g%3e%3cuse xlink:href='%23b' transform='rotate(45)'/%3e%3c/g%3e%3cuse xlink:href='%23c' transform='rotate(90)'/%3e%3c/g%3e%3cuse xlink:href='%23d' transform='rotate(180)'/%3e%3cg transform='translate(-2.02)'%3e%3cg id='f' transform='translate(37.962)'%3e%3cpath id='e' d='M5 0 1.618 1.176l-.073 3.58-2.163-2.854-3.427 1.037L-2 0z'/%3e%3cuse xlink:href='%23e' transform='scale(1 -1)'/%3e%3c/g%3e%3cuse xlink:href='%23f' transform='rotate(120)'/%3e%3cuse xlink:href='%23f' transform='rotate(-120)'/%3e%3c/g%3e%3c/g%3e%3c/svg%3e)
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)