Analysis of the Development Trend of Sports Research in China and Taiwan Using Natural Language Processing
Round 1
Reviewer 1 Report
This paper do analysis on the development trend of sports research in China and Taiwan to show the researches related sports. The auhtors use basic NLP technologies like TF-IDF. The overall analysis is useful for the sports eduction field. The structure is well-organised. I wish the authors should add some deep-learning based NLP technologies to better show the results. like word2vec, and some other topic models.
Author Response
- This paper do analysis on the development trend of sports research in China and Taiwan to show the researches related sports. The auhtors use basic NLP technologies like TF-IDF. The overall analysis is useful for the sports eduction field. The structure is well-organised. I wish the authors should add some deep-learning based NLP technologies to better show the results. like word2vec, and some other topic models.
Ans: Thanks for the insightful suggestions. The author has corrected in lines 418-419.
- The authors classify the content of the abstracts coming from the main sport scientific journals of China and Taiwan using NLP technique in order to highlight differences in research focus. The paper is written in a clear and comprehensible way. Nevertheless, the contribution of this paper is questionable.
Ans: Thanks for the insightful suggestions. NLP enables computers to understand natural language as humans do. Whether the language is spoken or written, natural language processing uses artificial intelligence to take real-world input, process it, and make sense of it in a way a computer can understand. At present, thanks to the rapidly developing new information technology, many scholars have opened their research results up to the world through online academic database pages (such as Google Scholar), in order to lay a good foundation for academic development. However, the speed of data generation and storage on various network platforms far exceeds the speed that people can analyze and digest, which also allows data mining and text mining technology to play an extremely important role in exploring the application of big data analysis. Through a rigorous NLP process, this study presents the current situation and differences of sports scholars in the two regions. Although the results of this research cannot clearly point out the focus of each article, it helps relevant scholars to grasp the general development direction of academic research.
Reviewer 2 Report
The authors classify the content of the abstracts coming from the main sport scientific journals of China and Taiwan using NLP technique in order to highlight differences in research focus. The paper is written in a clear and comprehensible way. Nevertheless, the contribution of this paper is questionable.
Major comments:
- the result of the article is a representation of the scope of research in the two countries. How this representation may be of interest to the reader or of help to the policymakers should be better elaborated in the discussion.
- the Discussion is almost entirely based on two references [39] and [40] that are in chinese and therefore not accessible to non-chinese speaking readers (including the reviewer)
- the core of the Conclusion (lines 404-407) is understandable and legitimate but is not supported by any of the results nor of the references
- clearly stating what is the objective of the article may benefit the entire structure of it
Minor revisions
- the introduction section contains many typos in the form of "-" in the middle of words
- abbreviations CCSCI and TSSCI in line 127 should be defined
- personal judgement such as "excellent" in line 136 should be avoided
- a large part of the Conclusion (lines 386-399 and 408-415) would be better placed in the discussion.
- it is not clear what the value/significance of the density of the network diagram is
Author Response
The authors classify the content of the abstracts coming from the main sport scientific journals of China and Taiwan using NLP technique in order to highlight differences in research focus. The paper is written in a clear and comprehensible way. Nevertheless, the contribution of this paper is questionable.
Ans: Thanks for the insightful suggestions. NLP enables computers to understand natural language as humans do. Whether the language is spoken or written, natural language processing uses artificial intelligence to take real-world input, process it, and make sense of it in a way a computer can understand. At present, thanks to the rapidly developing new information technology, many scholars have opened their research results up to the world through online academic database pages (such as Google Scholar), in order to lay a good foundation for academic development. However, the speed of data generation and storage on various network platforms far exceeds the speed that people can analyze and digest, which also allows data mining and text mining technology to play an extremely important role in exploring the application of big data analysis. Through a rigorous NLP process, this study presents the current situation and differences of sports scholars in the two regions. Although the results of this research cannot clearly point out the focus of each article, it helps relevant scholars to grasp the general development direction of academic research.
Major comments:
- the result of the article is a representation of the scope of research in the two countries. How this representation may be of interest to the reader or of help to the policymakers should be better elaborated in the discussion.
Ans: We have described in the text (lines 397-406)
- the Discussion is almost entirely based on two references [39] and [40] that are in chinese and therefore not accessible to non-chinese speaking readers (including the reviewer)
Ans: Thanks for the insightful suggestions. In the part of discussion, the following two Chinese references are more suitable to explain the history and current situation of related academic development in China. One of these references details the development of the sports-related fields in China over the past 70 years.
- the core of the Conclusion (lines 404-407) is understandable and legitimate but is not supported by any of the results nor of the references
Ans: References have been added to the text (line 418).
- clearly stating what is the objective of the article may benefit the entire structure of it
Ans: Thanks for the insightful suggestions. In order to make up for the shortcomings of the content analysis method, such as being time consuming, laborious, and not objective, this study proposes a program for analyzing and processing text data in sports-related fields based on the concept of NLP, which is different from the traditional content analysis method, with a faster automative analytical process and the ability to systematically extract and analyze the importance and relevance of keywords in abstract content (lines 46-52). Aadditionally, China and Taiwan share the same origins in terms of their history, culture, language, and text, coupled with the development of network information and the prevalence of digital collections, so that sports academic exchanges between the two regions benefit from the unprecedented application of information technology (IT), and have changed from the closed mode of the past to an open mode to create a good and mutually beneficial academic developmental environment (lines 33-38). Therefore, the purpose of research is to construct a suitable NLP analysis process for Chinese text mining. Through the rigorous NLP process, this study presents the current situations and differential results of sports academics in the two regions, which will help to create new opportunities and new directions for research and physical education development in an online environment (lines 97-101) . The above content is further explained in the introduction section.
- the introduction section contains many typos in the form of "-" in the middle of words
Ans: The typo in the text has been corrected.
- abbreviations CCSCI and TSSCI in line 127 should be defined
Ans: We have defined CCSCI and TSSCI in lines 125-127.
- personal judgement such as "excellent" in line 136 should be avoided
Ans: The author has modified it to "original articles with reference value" in line 136.
- a large part of the Conclusion (lines 386-399 and 408-415) would be better placed in the discussion.
Ans: The author has modified it from lines 384-421
- it is not clear what the value/significance of the density of the network diagram is
Ans: In social network analysis, the term network density refers to a measure of the prevalence of dyadic linkage or direct tie within a social network. A social network can be defined as a network formed by a set of interacting social entities (actors) and the linkages (relations or edges) among them. Therefore, density is used to judge the connection status of nodes, and a high-density network also means that the nodes have stronger cohesion, while degree centrality and K-Core can provide an understanding of the distribution or concentration of the overall network diagram [36,37] (lines 185-188)
Jacobs, W.; Goodson, P.; Barry, A.E.; McLeroy, K.R.; McKyer, E.L.; Valente, T.W. (2017). Adolescent social networks and alcohol use: variability by gender and type. Substance Use & Misuse, 2017, 52(4), 477-487.
Reviewer 3 Report
1. Need to justify for selecting the abstracts from July 2010 to June 2020? Is it only for the sake of 10 years? Can it be a random period? Any time-series analysis?
2. Why CKIP Chinese word segmentation system has been used? Are there any other systems considered for the problem at hand?
3. Why top two for Impact factor (IF) were selected? Is the problem oversimplified?
4. Line 127, what is CSSI and TSSI?
5. What version of the UCINET software used? Reference is needed for using the UCINET software.
6. In line 97, what do you mean by ‘rigorous’ NLP process?
7. Line 290, Figure 3 is not a network diagram.
8. Lines 308, 309, 310, a rewarding of the sentences are needed as the statements are explained in the section 4 (Discussion) section.
9. Lines 401, 402, what are the political and economic obstacles and restrictions? Some examples are needed.
10. In lines 408, 409, limitations of NLP are mentioned. But what are the limitations? Perhaps, need to be mentioned at end of section 1.
11. Line 411, what does the ‘macroscopic’ research results mean?
Author Response
Need to justify for selecting the abstracts from July 2010 to June 2020? Is it only for the sake of 10 years? Can it be a random period? Any time-series analysis?
Ans: Referring to the 10-year research interval of [16] and [31], this study retrieved the text abstracts of the two regions from July 2010 to June 2020, including 1,420 abstracts in China Sport Science and 1,142 abstracts in the Journal of Shanghai University of Sport, with a subtotal of 2,562 abstracts in China, 345 abstracts in the Physical Education Journal and 376 in Sports & Exercises Research. There was a subtotal of 721 abstracts in Taiwan, totaling 3,283 abstracts retrieved. (lines 139-144). The main purpose of this research is to compare the academic development trends of sports across the Taiwan Strait, and time series analysis can be listed as a future research direction. The main purpose of this study is to compare the development trend of sports academics in China and Taiwan, and time-series analysis can be listed as a future research direction.
Dobermann, D.; Hamilton, I. S. Publication patterns in developmental psychology: trends and social networks. International Journal of Psychology, 2017, 52 (4), 336-347.
Yang, D.H.; Wang, Y.; Yu, T.; Liu, X. Macro-level collaboration network analysis and visualization with essential science indicators: a case of social sciences. Malaysian Journal of Library & Information Science, 2020, 25(1), 121-138.
-Why CKIP Chinese word segmentation system has been used? Are there any other systems considered for the problem at hand?
Ans: Academia Sinica, the most preeminent academic institution of the Republic of China (Taiwan), was founded in China in 1928 to promote and undertake scholarly research in the sciences and humanities. This research use the Chinese word segmentation system developed by CKIP projects in Academia Sinica to identify the morphological information of each word phrases, and prune all words but noun phrases. Then, the keyword extraction algorithm proposed by is employed to extract keywords from continuous noun phrases. Therefore, the keywords extracted by this system are valuable for investigation.
-Why top two for Impact factor (IF) were selected? Is the problem oversimplified?
Ans: Thanks for the insightful suggestions. All TSSCI journals (only two journals) in the field of sports in Taiwan have been included in the research scope. In order to achieve the balance of the journals, we select the top two impact factor (IF) journals in China.
-Line 127, what is CSSI and TSSI?
Ans: We have defined CCSCI and TSSCI I in line 126-127.
-What version of the UCINET software used? Reference is needed for using the UCINET software.
Ans: UCINET 6 has added at 189 lines.
-In line 97, what do you mean by ‘rigorous’ NLP process?
Ans: The author has deleted 'rigorous'.
-Line 290, Figure 3 is not a network diagram.
Ans: The author modified it as Figure 5
-Lines 308, 309, 310, a rewarding of the sentences are needed as the statements are explained in the section 4 (Discussion) section.
Ans: The author has explained that in lines 398~406.
-Lines 401, 402, what are the political and economic obstacles and restrictions? Some examples are needed.
Ans: Thanks for the insightful suggestions. Political-economic barriers and constraints are a less clear-cut term. Since, China-Taiwan relations are so tense at the present time. Personally, it is a little awkward to make some examples in political and economic obstacles and restrictions.
-In lines 408, 409, limitations of NLP are mentioned. But what are the limitations? Perhaps, need to be mentioned at end of section 1.
Ans: The author has explained that in lines 70~84.
-Line 411, what does the ‘macroscopic’ research results mean?
Ans: The author has deleted 'rigorous'.
-It is suggested that related research can be supplemented by data mining technology to obtain more macroscopic research results.
Ans: Thanks for the insightful suggestions. The author has corrected in lines 418-419.
Round 2
Reviewer 1 Report
All have been revised
