Information Extraction for Computer Science Academic Rankings System

Shi, Chengkai; Quan, Jiahui; Li, Minglu

doi:10.1109/csc.2013.19

Cited by 7 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With research output, computer science underlies scientific publication metrics such as the hindex based on the number of citations from Scopus or the Web of Science (WoS) [280]. That underlies the computer science rank matrix as a study program that aims to extract, mine and rank academic information [281]. Thus, computer science is a science that keeps disclosing the output of its research through conferences and workshops.…”

Section: B Discussion: Accumulation and Spread -The Growth Overviewmentioning

confidence: 99%

Computer Science

Nasution¹,

Hidayat²,

Syah³

2022

International Journal on Advanced Science, Engineering and Information Technology

View full text Add to dashboard Cite

Possible for science itself, conceptually, to have and will understand differently, let alone science also seen as technology, such as computer science. After all, science and technology are viewpoints diverse by either individual, community, or social. Generally, it depends on socioeconomic capabilities. So it is with computer science has become a phenomenon and fashionable, where based on the stream of documents, various issues arise in either its theory or implementation, adapting different communities, or designing curriculum holds in the education system. Generally, there are gaps between rich and poor, masculine and feminine, and basic sciences, engineering, and social sciences in accessing and using computer science. In particular, there have been various developments in hardware, software, and brain-ware from computer science in the application. There are recurring problems shortly, in the same or different places, both in developed and technologically lagging countries. Although computer science is still new, it has provided various innovations through research, which is proven by many documents. Therefore, following the growth of computer science -documents in the reputable indexed database, Scopus -there are clues for showing the trends. That is, dividing documents into three-time sessions: sloping, increasing and decreasing. That is by using a growth graphic. Then equip it with some parameters: topics and the weights from hit counts of databases. It gives the meaning as an interpretation to support the reviews. Therefore, this paper will provide a commentary related to that growth. It is for showing that despite the spread of studies, at the last time-session, the issues were always present simultaneously at the same time in accumulation. That is for describing a study title of computer science about what the world already has, going, and will understand about computer science. It is a view regarding its philosophy, basic science, applications, and technology as concepts and solutions that make computer science the primary foundation for skills and professions in the 21 st century through the education system. Therefore, other scientific fields such as informatics, computer engineering, information science, information technology, and data science, which are at the crossroads of computer science, are also scientific fields that raise different issues.

show abstract

Section: B Discussion: Accumulation and Spread -The Growth Overviewmentioning

confidence: 99%

Computer Science

Nasution¹,

Hidayat²,

Syah³

2022

International Journal on Advanced Science, Engineering and Information Technology

View full text Add to dashboard Cite

show abstract

“…Szentirmai did a complete analysis of university rankings [23], considering cultural and geographical circumstances. His study examined the Times Higher Education WUR, Academic Ranking of World Universities, and the QS WUR, which are the most popular rankings.…”

Section: Related Workmentioning

confidence: 99%

A data analytics approach for university competitiveness: the QS world university rankings

Estrada-Real

Cantú-Ortiz

2022

Int J Interact Des Manuf

View full text Add to dashboard Cite

In recent years, higher education has felt pressured to prepare its graduates for the highly competitive international market due to globalization. Thus, many institutions have turned to position themselves well in university rankings as a way to attract the best academic and student talent from all over the world. Our work presents a predictive model for measuring university performance in the QS world university rankings (QS-WUR). We used a ten-year dataset to build models with statistical and machine learning algorithms contained in the library Caret of the RStudio software tool, to forecast global university position in QS-WUR. With these tools, we designed a methodology to predict the university partners' Final Scores based on their historical performance, achieving errors in the range of one or two points out of 100. The modelling may be a useful aid for university officers to develop strategies for improving institutional processes to attract the best students, faculty, and funding, enhance international collaboration and outlook, and foster international university prestige.

show abstract

“…[33][34][35][36]. Quan et al [37] proposed a paper classification and information extraction system in the computer science field. The team used the Naive Bayes algorithm to automatically classify a large number of papers and extract relevant information.…”

Section: Related Studies and The Current Contributionmentioning

confidence: 99%

DWSA: An Intelligent Document Structural Analysis Model for Information Extraction and Data Mining

Yue

2021

Electronics

View full text Add to dashboard Cite

The structure of a document contains rich information such as logical relations in context, hierarchy, affiliation, dependence, and applicability. It will greatly affect the accuracy of document information processing, particularly of legal documents and business contracts. Therefore, intelligent document structural analysis is important to information extraction and data mining. However, unlike the well-studied field of text semantic analysis, current work in document structural analysis is still scarce. In this paper, we propose an intelligent document structural analysis framework through data pre-processing, feature engineering, and structural classification with a dynamic sample weighting algorithm. As a typical application, we collect more than 11,000 insurance document content samples and carry out the machine learning experiments to check the efficiency of our framework. Meanwhile, to address the sample imbalance problem in the hierarchy classification task, a dynamic sample weighting algorithm is incorporated into our Dynamic Weighting Structural Analysis (DWSA) framework, in which the weights of different category tags according to the structural levels are iterated dynamically in training. Our results show that the DWSA has significantly improved the comprehensive accuracy and the classification F1-score of each category. The comprehensive accuracy is as high as 94.68% (3.36% absolute improvement) and the Macro F1-score is 88.29% (5.1% absolute improvement).

show abstract

Information Extraction for Computer Science Academic Rankings System

Cited by 7 publications

References 16 publications

Computer Science

Computer Science

A data analytics approach for university competitiveness: the QS world university rankings

DWSA: An Intelligent Document Structural Analysis Model for Information Extraction and Data Mining

Contact Info

Product

Resources

About