Customer Preference Analysis Based on SNS Data

Kim, J.S.; Yang, M.H.; Hwang, Yuan-Chu; Jeon, Seung‐Gyu; Kim, K.Y.; Jung, In-Sun; Choi, Chi-Hoon; Cho, W.S.; Na, J.H.

doi:10.1109/cgc.2012.109

Cited by 10 publications

(5 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Authors in [27] tried to evaluate customers' preferences on certain products based on social networks analysis and users' comments or posts. Using Hadoop big data, 600,000 Twitter comments from one month period are collected.…”

Section: Sentimnet Analysismentioning

confidence: 99%

A Near Real-Time Approach for Sentiment Analysis Approach Using Arabic Tweets

Zarrad¹

2019

JCP

View full text Add to dashboard Cite

Big data storage and real time data analysis are major challenges for IT researchers. The recent massive increase in data has not been accompanied by adequate storage technology and data processing algorithms. Understanding what people think about an idea, a product, a service or a policy is important for individuals, companies and governments. Sentiment analysis process can be used to identify opinions expressed in text on certain subjects. The result accuracy has a direct effect on decision making in both business and government. Our focus in this paper is first to identify the critical issues associated with real-time big data analysis and then to develop a new paradigm on Hadoop Ecosystem with real-time stream data processing to analyze Arabic tweet sentiment on Twitter. To perform real-time analytics, data collection should be performed using Apache Flume in order to move and aggregate all tweets received online (near real-time) to pre-defined locations through a channel called Sinks to the Hadoop distributed file system (HDFS). In addition, due to the serious challenges in Arabic text and speech and the high speed with which tweets arrive, we designed a complex sentiment analysis (SA) module to process each incoming tweet in such a way that no tweets are lost without being analyzed. Also, a sentiment analysis approach to Arabic text was developed using multiple Hive User Defended Functions (UDF). Finally, to guarantee a varied data collection, we proposed a Java MapReduce program for lexicon-based Arabic sentiment analysis, which supports n-gram search in the lexicon. Our approach was applied to determining opinions about MERS virus in the Kingdom of Saudi Arabia on Twitter Public Stream API and the results are discussed.

show abstract

Section: Sentimnet Analysismentioning

confidence: 99%

A Near Real-Time Approach for Sentiment Analysis Approach Using Arabic Tweets

Zarrad¹

2019

JCP

View full text Add to dashboard Cite

show abstract

“…Furthermore, a Q&A record consists of multiple sentences and paragraphs that provide users with enough space to present details. Essentially, user concerns, as well as their information needs, are closely correlated with the content they generate (Kaplan & Haenlein, 2010;Kim et al, 2012).…”

Section: Social Qanda Websitesmentioning

confidence: 99%

An investigation on the evolution of diabetes data in social Q&A logs

Zhao¹,

Chen²,

Zhang³

et al. 2018

Data and Information Management

View full text Add to dashboard Cite

This study investigates the evolution of diabetics’ concerns based on the analysis of terms in the Diabetes category logs on the Yahoo! Answers website. Two sets of question-and-answer (Q&A) log data were collected: one from December 2, 2005 to December 1, 2006; the other from April 1, 2013 to March 31, 2014. Network analysis and at-test were performed to analyze the differences in diabetics’ concerns between these two data sets. Community detection and topic evolution were used to reveal detailed changes in diabetics’ concerns in the examined period. Increases in average node degree and graph density imply that the vocabulary size that diabetics use to post questions decreases while the scope of questions has become more focused. The networks of key terms in the Q&A log data of 2005–2006 and 2013–2014 are significantly different according to thet-test analysis of the degree centrality and betweenness centrality. Specifically, there is a shift in diabetics’ focus in that they have become more concerned about daily life and other nonmedical issues, including diet, food, and nutrients. The recent changes and the evolution paths of diabetics’ concerns were visualized using an alluvial diagram. The food- and diet-related terms have become prominent, as deduced from the visualization results.

show abstract

“…In this section we limit ourselves to social subjects that use Big data technologies since it represents the main focus of this study. Kim et al [1] presented an approach to evaluate customers' preferences on certain products based on social networks analysis and users' comments or posts. The proposed approach uses Hadoop big data, to collect about 600,000 Twitter comments from one month period.…”

Section: Related Workmentioning

confidence: 99%

“…Nowadays, the growing importance of Social media coincides with the growth of big data technologies. To this end it is now possible to store a large amount of data being exchanged among people through social networks beyond traditional database systems [1]. McKinsey Global Institute estimates that consumers around the world stored more than six Exabyte (one Exabyte equal to 1,048,576 terabytes) of new data on devices such as PCs and notebooks which is equivalent to more than 4,000 times the information stored in the US Library of Congress [2].…”

Section: Introductionmentioning

confidence: 99%

The Evaluation of the Public Opinion - A Case Study: MERS-CoV Infection Virus in KSA

Zarrad

Jaloud

Alsmadi

2014

2014 IEEE/ACM 7th International Conference on Utility and Cloud Computing

View full text Add to dashboard Cite

Opinion Mining and Sentiment Analysis are active research trends in natural language processing and data mining. Recently, this research has been extended outside the computer science area to cover other areas such as social science, political science, and business. The explosion of social media such as social networks, Blogs, Twitter, and forums has created unprecedented opportunities for data mining research community. Analyzers can study and analyze users\u27 opinions, attitudes, and emotions about news or social events. Big data focuses on the intelligent analysis of a large amount of data that is typically collected from several different sources. Our focus in this work is to address new challenges raised by combining Apache Hadoop as a big data platform with an opinion mining approach to make a decision we often seek based on collected data from the opinions of people. We presented a case study about MERS virus in KSA to evaluate our proposed approach. A discussion of available dataset and results are also provided

show abstract

Customer Preference Analysis Based on SNS Data

Cited by 10 publications

References 1 publication

A Near Real-Time Approach for Sentiment Analysis Approach Using Arabic Tweets

A Near Real-Time Approach for Sentiment Analysis Approach Using Arabic Tweets

An investigation on the evolution of diabetes data in social Q&A logs

The Evaluation of the Public Opinion - A Case Study: MERS-CoV Infection Virus in KSA

Contact Info

Product

Resources

About