Ying Fang

Bio: Ying Fang is an academic researcher from Shangqiu Normal University. The author has contributed to research in topics: Overhead (computing) & Erasure code. The author has an hindex of 1, co-authored 3 publications receiving 35 citations.

Multi-Strategy Sentiment Analysis of Consumer Reviews Based on Semantic Fuzziness

Abstract: Since Internet has become an excellent source of consumer reviews, the area of sentiment analysis (also called sentiment extraction, opinion mining, opinion extraction, and sentiment mining) has seen a large increase in academic interest over the last few years. Sentiment analysis mines opinions at word, sentence, and document levels, and gives sentiment polarities and strengths of articles. As known, the opinions of consumers are expressed in sentiment Chinese phrases. But due to the fuzziness of Chinese characters, traditional machine learning techniques can not represent the opinion of articles very well. In this paper, we propose a multi-strategy sentiment analysis method with semantic fuzziness to solve the problem. The results show that this hybrid sentiment analysis method can achieve a good level of effectiveness.

A Faster Read and Less Storage Algorithm for Small Files on Hadoop

Abstract: Massive small files access is the main challenge for the Hadoop Distributed File System. To solve these problems, we present a new Algorithm of archive file, A Faster Read and Less Storage Algorithm for Small Files on Hadoop. A new logical file name is used to identify the file which generated by the pair in the name node. Our experiments show that the algorithm is around 76.6% faster than original HDFS in the time of file storing, and around 31.9.6% faster than original HDFS in the time of file reading, around 73.9% less than original HDFS in the memory consumption of namenode.

CLRC: a New Erasure Code Localization Algorithm for HDFS

Abstract: With the continuous development of big data, the increase speed of hardware expansion used for HDFS has been far behind the volume of big data. As a data redundancy strategy, the traditional data replication strategy has been gradually replaced by Erasure Code due to its smaller redundancy rate and storage overhead. However, compared with replicas, Erasure Code needs to read a certain amount of data blocks during the process of data recovery, resulting in a large amount overhead of I/O and network. Based on the RS algorithm, a new CLRC algorithm is proposed to optimize the locality of RS algorithm by grouping RS coded blocks and generating local check blocks. Evaluations show that the algorithm can reduce about 61% bandwidth and I/O consumption during the process of data recovery when a single block is damaged. What's more, the cost of decoding time is only 59% of RS algorithm.

Sentiment Analysis for E-Commerce Product Reviews in Chinese Based on Sentiment Lexicon and Deep Learning

Abstract: In recent years, with the rapid development of Internet technology, online shopping has become a mainstream way for users to purchase and consume. Sentiment analysis of a large number of user reviews on e-commerce platforms can effectively improve user satisfaction. This paper proposes a new sentiment analysis model-SLCABG, which is based on the sentiment lexicon and combines Convolutional Neural Network (CNN) and attention-based Bidirectional Gated Recurrent Unit (BiGRU). In terms of methods, the SLCABG model combines the advantages of sentiment lexicon and deep learning technology, and overcomes the shortcomings of existing sentiment analysis model of product reviews. The SLCABG model combines the advantages of the sentiment lexicon and deep learning techniques. First, the sentiment lexicon is used to enhance the sentiment features in the reviews. Then the CNN and the Gated Recurrent Unit (GRU) network are used to extract the main sentiment features and context features in the reviews and use the attention mechanism to weight. And finally classify the weighted sentiment features. In terms of data, this paper crawls and cleans the real book evaluation of dangdang.com, a famous Chinese e-commerce website, for training and testing, all of which are based on Chinese. The scale of the data has reached 100000 orders of magnitude, which can be widely used in the field of Chinese sentiment analysis. The experimental results show that the model can effectively improve the performance of text sentiment analysis.

User Rating Classification via Deep Belief Network Learning and Sentiment Analysis

Abstract: Deep learning is a methodology applied across many fields. User comments are important for recommender systems because they include various types of emotional information that may influence the correctness or precision of the recommendation. Improving the accuracy of user ratings from obtained feasible recommendations is essential. In this paper, we propose a deep learning model to process user comments and to generate a possible user rating for user recommendations. First, the system uses sentiment analysis to create a feature vector as the input nodes. Next, the system implements noise reduction in the data set to improve the classification of user ratings. Finally, a deep belief network and sentiment analysis (DBNSA) achieves data learning for the recommendations. The experimental results indicated that this system has better accuracy than traditional methods.

360 degree view of cross-domain opinion classification: a survey

Abstract: In the field of natural language processing and text mining, sentiment analysis (SA) has received huge attention from various researchers’ across the globe. By the prevalence of Web 2.0, user’s became more vigilant to share, promote and express themselves along with any issues or challenges that are being encountered on daily activities through the Internet (social media, micro-blogs, e-commerce, etc.) Expression and opinion are a complex sequence of acts that convey a huge volume of data that pose a challenge for computational researchers to decode. Over the period of time, researchers from various segments of public and private sectors are involved in the exploration of SA with an aim to understand the behavioral perspective of various stakeholders in society. Though the efforts to positively construct SA are successful, challenges still prevail for efficiency. This article presents an organized survey of SA (also known as opinion mining) along with methodologies or algorithms. The survey classifies SA into categories based on levels, tasks, and sub-task along with various techniques used for performing them. The survey explicitly focuses on different directions in which the research was explored in the area of cross-domain opinion classification. The article is concluded with an objective to present an exclusive and exhaustive analysis in the area of opinion mining containing approaches, datasets, languages, and applications used. The observations made are expected to support researches to get a greater understanding on emerging trends and state-of-the-art methods to be applied for future exploration.

Applying sentiment analysis to automatically classify consumer comments concerning marketing 4Cs aspects

Abstract: With the rapid development of science and technology, consumers are used to searching online for evaluations before purchasing products. Manufacturers can also utilize such information like users’ usage habits, browsed websites, comments, messages, etc. to formulate marketing strategies suitable for their products. Several researches developed opinion mining on predicting the polarity of consumers’ comments, but few of them were from marketing point of view. In this regards, this study looks to establish an automated way to collect and analyze consumers’ comments in social networks, automatically classify them into marketing 4Cs and non-marketing categories from a large number of consumer comments, and divide the category of marketing 4Cs articles into four types of attribute dimensions to analyze emotional polarity. Based on the marketing theory of 4Cs and LDA topic analysis, this study extracted the characteristic keywords from the collected consumer reviews for corpus classification and sentiment polarity analysis. This study further establishes a feature keyword library for specific fields, hoping to improve the accuracy of sentiment analysis through these keywords, simplify the process of consumers’ searches for product evaluations, and facilitate consumers to search for helpful target information.