Authors:
Hannan Afzal, Muhammad Qasim Ali, Kafait Ullah, Muhammad Zubair Qasim

Addresses:
Department of Business Administration, University of Sialkot, Sialkot, Punjab, Pakistan. Department of Education, University of Sialkot, Sialkot, Punjab, Pakistan. Faculty of Management and Administrative Sciences, University of Sialkot, Sialkot, Punjab, Pakistan. Department of Computer Science, Govt. High School 43/WB, Vehari, Punjab, Pakistan.

Abstract:

The existing study examines the ongoing disconnect between conventional financial modeling and the governance of unstructured data, preventing the accurate valuation of intangible assets, a key component of the information economy. To improve valuation accuracy, the study uses multimodal deep learning methods and a scientometric evaluation to visualize the intellectual space and the discipline's development. A graphical representation of the domain architecture was generated using VOSviewer, which visualizes a large body of information gathered from major academic databases. The results indicate that the research is dominated by an Anglo-American research alliance that includes powerful players such as Google, Microsoft, Stanford, MIT, and the United States, which is leading in research volume, influence, and collaboration. At the same time, a new research center, spearheaded by China, is emerging in Asia. Analyses of citations point to the work of Erik Cambria in sentiment analysis and to that of Yoshua Bengio in deep learning. The keyword mapping helps identify key themes around big data, benchmark datasets, empirical performance metrics (accuracy and predictive power), and the significance of global scientific competition and collaboration facilitated by conferences. Generally, the research finds that although concentrated authorship is a faster method of innovation, it reduces diversity, and it is important to note that there is still a need to develop stronger AI systems capable of quantifying intangible assets.

Keywords: Intangible Asset Valuation; Unstructured Data; Sentiment Analysis; Deep Learning (DL); Financial Modeling; Scientometric Evaluation; Global Scientific Competition.

Received on: 19/09/2025, Revised on: 14/11/2025, Accepted on: 07/01/2026, Published on: 19/08/2026

DOI: 10.69888/FTSFDS.2026.000740

FMDB Transactions on Sustainable Finance and Data Science, 2026 Vol. 1 No. 3, Pages: 131-144

• Views : 38
• Downloads : 8

Download PDF