Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Industrial and Systems Engineering | en_US |
| dc.contributor.advisor | Tsui, Eric (ISE) | - |
| dc.contributor.advisor | Cheung, Benny (ISE) | - |
| dc.creator | Cai, Linlin | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/8574 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | Intelligent extraction of intellectual capital for value creation in knowledge-intensive organizations | en_US |
| dcterms.abstract | Since the world's economy has rapidly changed from industrial-based to knowledge based, it is pressing for organizations to identify Intellectual Capital (IC) in time and disclose as well as track this kind of important knowledge-based capital timely and accurately, which by doing so not only can improve decision-making processes internally, but also can demonstrate the organizational competitiveness externally. Due to the dynamics and complexity of IC, it remains a significant challenge for organizations and researchers to extract IC from the multitude of materials such as annual reports, IPO prospectuses, sustainability reports, large volume of interview transcripts as well the space of social media, etc. The conventional method of extracting IC-related information heavily relies on manual content analysis. However, because it is highly time-consuming, the manual method loses its popularity both in academia and in industry, automatic extraction methods that are assisted by computers offer great help to cope with the huge volume of data. However, these computer-assisted methods have the shortfalls of ignoring the context in practical utilization, the complexity of IC components, and the difficulty to replicate the process as well as low accuracy in terms of extraction which also compromises this method's effectiveness to be used in the public domain and on a large scale. Redressing these problems, an intelligent methodology is designed by using the computational linguistics and artificial intelligence (AI) techniques to extract and analyze IC-related information automatically and intelligently. The demonstrated intelligence is manifested in several ways. Firstly, an IC knowledge repository is constructed based on the IC-related keywords/phrases and keywords combination patterns which consist of the IC academic and practical repositories. The established IC knowledge repository offers sources of matching words to extract IC-related information. Based on the IC knowledge repository, an IC information extraction algorithm is designed to achieve the goal of extracting the IC information automatically. In this step, the knowledge-based intellectual capital extraction (KBICE) algorithm increases the efficiency of extracting IC-related information. The repository together with the algorithm helps to identify IC-related sentences and paragraphs more accurately and faster than the methods merely using the IC terms checklist. IC sentimental analysis determines the overall nature of the extracted IC information from a news-tenor perspective which can recognize news from negative and positive perspective. | en_US |
| dcterms.abstract | Through setting up an IC knowledge repository, IC-related keywords/phrases improve the ability of extracting practical IC information used. The keywords extraction patterns express the inter-relationship of IC components and increase the accuracy and relevance of the extraction. The dynamic IC term checklist enables the same methodology to be used in various contexts. With this added knowledge, the IC sentimental analysis greatly increases the relevance of Intelligent Extraction of Intellectual Capital (IEIC) in IC research and application development in terms of determining whether the extracted IC information is indeed positive or negative. After conducting the experiment by using company reports containing IC information, the two parts' results are very encouraging when compared with other existing methods. In testing the KBICE)algorithm, three standards including precision, recalls as well F-measure are adopted to measure the usability of KBICE. Compared to rule-based reasoning (RBR) and bag-of-words (BoW) models, KBICE has demonstrated better results. In testing the sentimental analysis, the processed results of testing IC sentimental analysis of IC news also exhibited high recall and precision accuracies. Meanwhile, processing company annual reports and online news that contain IC has shown that IEIC can help to produce IC integrated reports. The reports, despite their decline in popularity, can be produced timely and contain more comprehensive information than the conventional manually compiled version. This research has reveals additional challenges for intelligent extraction of IC information. Many aspects still need to be improved. More refinements need to be made to the automatic extract algorithm to reduce the subjectivity. Companies in more industries also need to be involved by offering more comprehensive data. In addition to IC news, other IC critical information such as employees' social media should also undergo the IC sentimental analysis. | en_US |
| dcterms.extent | xv, 95 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2016 | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.educationalLevel | M.Phil. | en_US |
| dcterms.LCSH | Intellectual capital -- Management. | en_US |
| dcterms.LCSH | Intellectual property. | en_US |
| dcterms.LCSH | Knowledge management. | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | open access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b29108792.pdf | For All Users | 1.53 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/8574