28 research outputs found
An Analysis of Benefits and Risks of Artificial Intelligence
No full textArtificial intelligence AI is now typical technology in our everyday lives with applications in image and voice recognition, language translations, chatbots, and predictive data analysis. AI technological progress is likely to present us with many challenges. Furthermore, AI increasingly complex algorithms currently influence our lives and our civilization more than ever before. AI should be taken very seriously even if the probability of their rate were low. Our focus on this paper is an analysis of benefits and risks of AI was on highlighting the potential vulnerabilities and inequities that the use of AI executes. Win Mar | Yin Myo Kay Khine Thaw "An Analysis of Benefits and Risks of Artificial Intelligence" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-3 | Issue-5 , August 2019, URL: https://www.ijtsrd.com/papers/ijtsrd26667.pd
Understanding the Determinants of Security and Privacy in Cloud Computing Architecture
No full textCloud computing is an emerging model of business computing. Cloud computing is a service, which offers customers to work over the internet. It simply states that cloud computing means storing and accessing the data and programs over the internet rather than the computer's hard disk. The data can be anything such as music, files, images, documents, and many more. The user can access the data from anywhere just with the help of an internet connection. To access cloud computing, the user should register and provide with ID and password for security reasons. The speed of transfer depends on various factors such as internet speed, the capacity of the server, and many more. In this paper, we explore the understanding the determinates of security and privacy in cloud computing, Cloud Computing architecture and We also address the characteristics and applications of several popular cloud computing platforms. We identified several challenges from the cloud computing adoption perspective and we also highlighted the cloud interoperability issue that deserves substantial further research and development. However, security and privacy issues present a strong barrier for users to adapt to cloud computing systems. Yin Myo Kay Khine Thaw | Khin Myat Nwe Win "Understanding the Determinants of Security and Privacy in Cloud Computing Architecture" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-3 | Issue-5 , August 2019, URL: https://www.ijtsrd.com/papers/ijtsrd26452.pd
Online Buying in Virtual Cosmetic Marketplace Using Recommender System
No full textElectronic Commerce (E-commerce) has become one of the essential characteristics in the Internet era. Nowadays, E-commerce is growing rapidly in the Internet, and has become a complement to the usual business activities of corporations and individuals. Recommender systems have evolved in the last years as specialized tools to assist users in a plethora of computer-mediated tasks by providing guidelines or hints. Most recommender systems are aimed at helping users to deal with the problem of information overload by facilitating access to relevant items.In this system, shopping agents like buying agents, selling agents, and mall agents, and then knowledge-based recommender system are used because the World Wide Web information grows explosively in the Internet and people encounter problem to pick some correct things from the set of choice in E-Commerce. All the activities are done in Virtual Marketplace. Virtual Marketplace is a type of E-Marketplace system. In this system, recommender systems help users choose something they actually want or need and limit their search by supplying a list of items. Therefore, the recommender systems get vital role in the Internet. The objective of the system is to give effective products for user when they want to search cosmetic as to which type of cosmetic is suitable for them. Knowledge-based recommender system and implementation with a multi-agent system framework for marketplace system are used in this system, in which buying agent, selling agent and mall agent are presented
Assigning Polarity Scores to Facebook Myanmar Movie Comments
No full textUser-generated texts such as reviews, discussions or comments are valuable indicators of users’ preferences. Apart from binary classification (positive or negative) of the reviews, some researchers calculated polarity scores that give a very concise summary and provide more information of the reviews. In this paper, a system for assigning polarity scores to Facebook Myanmar movie comments is proposed. Myanmar is a language with underdeveloped electric resources. As this is pioneering work for this combination of language and sentiment analysis, the polarity scores of each positive and negative word in the movie domain-specific polarity lexicon is calculated. And then the polarity scores to each comment of the plain text movie corpus are assigned. The proposed system achieves 89% and 85% accuracy on positive and negative opinion words respectively in the evaluation of polarity score lexicon. We also make the comment polarity for 3-class evaluation and 5-class evaluation based on the scores of comments
Assigning Polarity Scores to Facebook Myanmar Movie Comments
No full textUser-generated texts such as reviews, discussions or comments are valuable indicators of users’ preferences. Apart from binary classification (positive or negative) of the reviews, some researchers calculated polarity scores that give a very concise summary and provide more information of the reviews. In this paper, a system for assigning polarity scores to Facebook Myanmar movie comments is proposed. Myanmar is a language with underdeveloped electric resources. As this is pioneering work for this combination of language and sentiment analysis, the polarity scores of each positive and negative word in the movie domain-specific polarity lexicon is calculated. And then the polarity scores to each comment of the plain text movie corpus are assigned. The proposed system achieves 89% and 85% accuracy on positive and negative opinion words respectively in the evaluation of polarity score lexicon. We also make the comment polarity for 3-class evaluation and 5-class evaluation based on the scores of comments
An analysis of YouTube videos for teaching information literacy skills
No full textTraditionally librarians and educators have been using a variety of methods such as lectures, discussions, demonstrations, and hand-on sessions for imparting information literacy skills. An exciting addition to such initiatives is the availability of Web 2.0 applications. Among the Web 2.0 tools, YouTube is quickly becoming a new way of teaching information literacy skills in a more interesting and engaging manner. The purpose of this study was to analyze information literacy videos on YouTube using the Big6 information literacy model. This paper also makes certain suggestions for using YouTube for imparting information literacy skills effectively
Multi-Aspect Attention Model for Aspect-based Sentiment Classification Using Deep Learning
No full textSentiment Aware Word Embedding Approach for Sentiment Analysis
No full textNowadays, many business owners want to know the feedback of their products. If they get the feedback from customers, they can promote the quality of their products. So, Sentiment analysis has become a popular research problem to tackle in NLP field. It is the process of identifying whether the opinion or reviews expressed in a piece of work is positive, negative or neutral. We can apply sentiment analysis in brand monitoring, customer service, market research and analysis. Word embedding step is a problem in sentiment analysis of neural network models. Most existing algorithms for continuous word representation typically only model the syntactic context of words but ignore the sentiment of text. It is a problematic for sentiment analysis as they usually map words with similar syntactic context but ignore opposite sentiment polarity, such as good and bad, like and dislike. We solve this issue by proposing a method, sentiment-aware word embedding (SAWE). SAWE encodes sentiment information in the continuous representation of words by using (1) prediction the model and (2) ranking model. Finally, we evaluate our proposed method on IMDB movie review and twitter datasets, after that we prove our method outperform than other word embedding methods like word2vec and GloVe
Aspect Level Sentiment Analysis Using Bi-Directional LSTM Encoder with the Attention Mechanism
No full text
