Talk Show’s Business Intelligence on Television by Using Social Media Data in Indonesia

Electronic ticket (eticket) provider services are growing fast in Indonesia, makingthe competition between companies increasingly intense. Moreover, most of them have the sameservice or feature for serving their customers. To get back the feedback of their customers, manycompanies use social media (Facebook and Twitter) for marketing activity or communicatingdirectly with their customers. The development of current technology allows the company totake data from social media. Thus, many companies take social media data for analyses. Thisstudy proposed developing a data warehouse to analyze data in social media such as likes,comments, and sentiment. Since the sentiment is not provided directly from social media data,this study uses lexicon based classification to categorize the sentiment of users’ comments. Thisdata warehouse provides business intelligence to see the performance of the company based ontheir social media data. The data warehouse is built using three travel companies in Indonesia.As a result, this data warehouse provides the comparison of the performance based on the socialmedia data.

Download Full-text

Social Media and Corporate Data Warehouse Environments

International Journal of Business Intelligence Research ◽

10.4018/jbir.2012040101 ◽

2012 ◽

Vol 3 (2) ◽

pp. 1-12 ◽

Cited By ~ 2

Author(s):

Debora S. Bartoo

Keyword(s):

Social Media ◽

Data Warehouse ◽

Business Intelligence ◽

Data Warehouses ◽

Social Media Data ◽

Hands On ◽

Media Data

This paper argues that organizations need to prepare for the integration of social media data into their data warehouses in order to fully understand their customers. Social media has quickly gained acceptance in its adoption and use and firms are eager to get their hands on it to better understand customer sentiment. However, social media data is different and more complex than traditional data and most data warehouses are not structured in a way for BI applications to easily make sense it. As a result, it is becoming critical for business intelligence teams to begin to understand the challenges this data presents and to better plan for the integration of this information into corporate data warehouses.

Download Full-text

Optimizing Search and Data Analytics of Twitter Data using Elastic Search Algorithms

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.f1535.089620 ◽

2020 ◽

Vol 9 (6) ◽

pp. 427-433

Keyword(s):

Social Media ◽

Business Intelligence ◽

Data Analytics ◽

Distributed Search ◽

Time Data ◽

Social Media Data ◽

Twitter Data ◽

Crucial Part ◽

Media Data ◽

Better Than

Quick data acquisition and analysis became an important tool in the contemporary era. Real time data is made available in World Wide Web (WWW) and social media. Especially social media data is rich in opinions of people of all walks of life. Searching and analysing such data provides required business intelligence (BI) for applications of various domains in the real world. The application may be in the area of politics or banking or insurance or healthcare industry. With the emergence of cloud computing, volumes of data are added to cloud storage infrastructure and it is growing exponentially. In this context, Elasticsearch is the distributed search and analytics engine that is very crucial part of Elastic Stack. For data collection, aggregation and enriching it Beats and Logstash are used and such data is stored in Elasticsearch. For interactive exploration and visualization Kibana is used. Elasticsearch helps in indexing of data, searching efficiently and performing data analytics. In this paper, the utility of Elasticsearch is evaluated for optimising search and data analytics of Twitter data. Empirical study is made with the Elasticsearch tool configured for Windows and also using Amazon Elasticsearch and the results are compared with state of art. The experimental results revealed that the Elasticsearch performs better than the existing ones.

Download Full-text

Beyond Sentiment Classification: A Novel Approach for Utilizing Social Media Data for Business Intelligence

International Journal of Advanced Computer Science and Applications ◽

10.14569/ijacsa.2020.0110355 ◽

2020 ◽

Vol 11 (3) ◽

Author(s):

Ibrahim Said Ahmad ◽

Azuraliza Abu ◽

Mohd Ridzwan ◽

Mohammad Darwich

Keyword(s):

Social Media ◽

Business Intelligence ◽

Sentiment Classification ◽

Social Media Data ◽

Novel Approach ◽

Media Data

Download Full-text

Managing extracted knowledge from big social media data for business decision making

Journal of Knowledge Management ◽

10.1108/jkm-07-2015-0296 ◽

2017 ◽

Vol 21 (2) ◽

pp. 275-294 ◽

Cited By ~ 36

Author(s):

Wu He ◽

Feng-Kwei Wang ◽

Vasudeva Akula

Keyword(s):

Social Media ◽

Big Data ◽

Business Intelligence ◽

Business Decisions ◽

Business Decision ◽

Social Media Data ◽

Content Type ◽

Media Data ◽

Big Data Technology

Purpose This paper aims to propose a knowledge management (KM) framework for leveraging big social media data to help interested organizations integrate Big Data technology, social media and KM systems to store, share and leverage their social media data. Specifically, this research focuses on extracting valuable knowledge on social media by contextually comparing social media knowledge among competitors. Design/methodology/approach A case study was conducted to analyze nearly one million Twitter messages associated with five large companies in the retail industry (Costco, Walmart, Kmart, Kohl’s and The Home Depot) to extract and generate new knowledge and to derive business decisions from big social media data. Findings This case study confirms that this proposed framework is sensible and useful in terms of integrating Big Data technology, social media and KM in a cohesive way to design a KM system and its process. Extracted knowledge is presented visually in a variety of ways to discover business intelligence. Originality/value Practical guidance for integrating Big Data, social media and KM is scarce. This proposed framework is a pioneering effort in using Big Data technologies to extract valuable knowledge on social media and discover business intelligence by contextually comparing social media knowledge among competitors.

Download Full-text