Multidimensional Author Profiling for Social Business Intelligence

Lanza-Cruz, Indira; Berlanga, Rafael; Aramburu, María José

doi:10.1007/s10796-023-10370-0

Cited by 3 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To overcome this limitation, we need to develop more automated and robust techniques. Our initial approach involves a user classification into business roles, a process that can be further refined and automated through the implementation of advanced NLP text classifiers (Nebot et al 2018;Lanza-Cruz et al 2023). This will facilitate the identification of relevant users aligned with specific analytical goals.…”

Section: Discussionmentioning

confidence: 99%

A Data Quality Multidimensional Model for Social Media Analysis

Aramburu,

Berlanga,

Lanza-Cruz

2023

Bus Inf Syst Eng

Self Cite

View full text Add to dashboard Cite

Social media platforms have become a new source of useful information for companies. Ensuring the business value of social media first requires an analysis of the quality of the relevant data and then the development of practical business intelligence solutions. This paper aims at building high-quality datasets for social business intelligence (SoBI). The proposed method offers an integrated and dynamic approach to identify the relevant quality metrics for each analysis domain. This method employs a novel multidimensional data model for the construction of cubes with impact measures for various quality metrics. In this model, quality metrics and indicators are organized in two main axes. The first one concerns the kind of facts to be extracted, namely: posts, users, and topics. The second axis refers to the quality perspectives to be assessed, namely: credibility, reputation, usefulness, and completeness. Additionally, quality cubes include a user-role dimension so that quality metrics can be evaluated in terms of the user business roles. To demonstrate the usefulness of this approach, the authors have applied their method to two separate domains: automotive business and natural disasters management. Results show that the trade-off between quantity and quality for social media data is focused on a small percentage of relevant users. Thus, data filtering can be easily performed by simply ranking the posts according to the quality metrics identified with the proposed method. As far as the authors know, this is the first approach that integrates both the extraction of analytical facts and the assessment of social media data quality in the same framework.

show abstract

Section: Discussionmentioning

confidence: 99%

A Data Quality Multidimensional Model for Social Media Analysis

Aramburu,

Berlanga,

Lanza-Cruz

2023

Bus Inf Syst Eng

Self Cite

View full text Add to dashboard Cite

show abstract

“…to improve business performance. This concept has also been researched previously (Lanza-Cruz, 2024). https://internationalpublisher.id/journal/index.php/Lejea Business Intelligence is a combination of mathematical models and analytical methodologies designed systematically to form data so as to produce information and knowledge that is useful in supporting complex decision-making processes (Mohammed, 2024).…”

Section: Literatur Review a Business Inteligencementioning

confidence: 99%

Business Intelligence HRIS Monitoring Dashboard to Increase User Interaction Using Power BI

Listiana

2024

LEJEA

View full text Add to dashboard Cite

PT Samudra Dyan Praga is a company operating in the exhibition contracting industry with national and international reach, which has several branches throughout Indonesia. The implementation of exhibition events which often take place simultaneously, as well as the dynamic movement of the workforce, creates its own challenges in terms of reporting employee data. The process of updating data to reporting still relies heavily on separate spreadsheets, thus hampering data recapitulation, analysis and management decision-making processes related to human resources. The main goal of this research is to improve dashboard visualization to support decision making, Business Intelligence (BI) analysis, as well as ensure wider accessibility for users. We identify the latest trends and implement visualization dashboard practices in the BI domain. With a user-focused design approach, we provide improvements and solutions. Specifically, we addressed several challenges, such as creating dashboard controls that are easily accessible to novice users in visualization, improving annotation capabilities to support BI analysts in the analysis process, and adding storytelling functionality to dashboards to facilitate communication between analysts and decision makers. We specifically focused on new aspects of annotation, such as multi-target annotation, annotation transparency across charts, and the ability to share annotations between multiple data sources and BI applications. Through interviews with BI analytics experts and gathering requirements related to BI visual storytelling, we designed and implemented a storytelling tool prototype integrated in the dashboard analytics tool. This allows for a seamless transition from analysis to story creation and sharing.Our system was previously identified by experts as having great potential for training other analysts. Furthermore, it helps BI analysts compile and convey their findings more quickly to decision makers, as well as enabling them to reach a wider audience because the results of data analysis are presented in an easy-to-understand format without the need for special training.

show abstract

RETRACTED: Design and Implementation of Folk Arts and Crafts Resource Library System Based on Ontology Description and Random Matrix

Lei

2024

International Journal of Ambient Computing and Intelligence

View full text Add to dashboard Cite

This article first constructs an ontology, designs the ontology of the resource library, and then uses the ontology to generate formatted SMD. It uses semantic elements to standardize the description of system resources, organizes folk arts and crafts resources in a machine understandable manner, and presents semantic features to users in an intuitive manner. And use random matrix theory to extract the correlation between data from massive amounts of data. The experimental results show that the running time of the system algorithm reaches 1.8 seconds, effectively avoiding the algorithm's extended state estimation falling into local optima and greatly reducing the computational complexity of the algorithm. This study is conducive to promoting the role of resource library systems and improving retrieval efficiency.

show abstract

Multidimensional Author Profiling for Social Business Intelligence

Cited by 3 publications

References 36 publications

A Data Quality Multidimensional Model for Social Media Analysis

A Data Quality Multidimensional Model for Social Media Analysis

Business Intelligence HRIS Monitoring Dashboard to Increase User Interaction Using Power BI

RETRACTED: Design and Implementation of Folk Arts and Crafts Resource Library System Based on Ontology Description and Random Matrix

Contact Info

Product

Resources

About