基于改进PositionRank算法的高校教师自我评价关键词提取方法

doi:10.13229/j.cnki.jdxbgxb.20250273

吉林大学学报(工学版) ›› 2025, Vol. 55 ›› Issue (8): 2753-2760.doi: 10.13229/j.cnki.jdxbgxb.20250273

• 计算机科学与技术 • 上一篇

基于改进PositionRank算法的高校教师自我评价关键词提取方法

齐晓亮¹(),陈海鹏²,石泽男²(),王守佳¹

^1.吉林大学人力资源处，长春 130012
^2.吉林大学计算机科学与技术学院，长春 130012

收稿日期:2025-03-31 出版日期:2025-08-01 发布日期:2025-11-14
通讯作者: 石泽男 E-mail:qixl@jlu.edu.cn;shizn@jlu.edu.cn
作者简介:齐晓亮（1978-），男，副教授. 研究方向：高校人力资源管理与信息化建设. E-mail：qixl@jlu.edu.cn
基金资助:
国家自然科学基金面上项目(62276112)

Keyword extraction method for university faculty self-evaluations based on the improved PositionRank algorithm

Xiao-liang QI¹(),Hai-peng CHEN²,Ze-nan SHI²(),Shou-jia WANG¹

^1.Human Resources Department，Jinlin University，Changchun 130012，China
^2.College of Computer Science and Technology，Jilin University，Changchun 130012，China

Received:2025-03-31 Online:2025-08-01 Published:2025-11-14
Contact: Ze-nan SHI E-mail:qixl@jlu.edu.cn;shizn@jlu.edu.cn

摘要/Abstract

摘要：

针对教师自我评价存在评价过程主观性较强、工作效率低下以及精准度不高等问题，本文提出了基于改进PositionRank算法的高校教师自我评价关键词提取方法。首先，对教师自我评价数据进行采集和清洗，去除冗余与异常数据以提高数据质量；其次，采用基于图的关键词抽取算法生成高质量标签数据；最后，通过改进后的PositionRank算法自适应学习词组间的注意力权重，实现关键词的精准提取。实验结果表明：该方法能高效识别教师评价中的关键内容，显著提高关键词提取的准确性，同时具备较强的评价一致性，有助于揭示教师的核心优势与改进方向，为完善高校教师评价体系提供了有力的技术支撑。

关键词: 高校教师自我评价, 关键词提取, 自适应学习, 注意力权重

Abstract:

The evaluation reform of university faculty is an important component of educational evaluation reform and a crucial guarantee for stimulating the intrinsic motivation of university faculty. Self-evaluation by faculty is a key aspect of the comprehensive evaluation system for university faculty. Currently， self-evaluation largely relies on manual statistics and analysis， which presents issues such as strong subjectivity in the evaluation process， low work efficiency， and poor accuracy. Therefore， this paper proposes a method for extracting keywords from university faculty self-evaluation based on an improved PositionRank algorithm. First， faculty self-evaluation data is collected and cleaned to remove redundant and anomalous data， improving data quality. Second， a graph-based keyword extraction algorithm is used to generate high-quality label data. Finally， the improved PositionRank algorithm is employed to adaptively learn the attention weights between phrases， achieving accurate keyword extraction. Experimental results show that this method efficiently identifies key content in faculty evaluations， significantly improving the accuracy of keyword extraction while demonstrating strong evaluation consistency. It helps reveal the core strengths and areas for improvement of faculty and provides strong technical support for improving the university faculty evaluation system.

Key words: self-evaluation of university faculty, keyword extraction, adaptive learning, attention weight

中图分类号:

齐晓亮,陈海鹏,石泽男,王守佳. 基于改进PositionRank算法的高校教师自我评价关键词提取方法[J]. 吉林大学学报(工学版), 2025, 55(8): 2753-2760.

Xiao-liang QI,Hai-peng CHEN,Ze-nan SHI,Shou-jia WANG. Keyword extraction method for university faculty self-evaluations based on the improved PositionRank algorithm[J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(8): 2753-2760.

图/表 6

图1

图2

表1

图3

表2

表3

参考文献 22

[1]	胡瑞, 李彩云. 高校教师评价改革的“破”与“立”——基于新公共服务理论的分析框架[J]. 现代教育管理, 2024 (8): 99-107.
	Hu Rui, Li Cai-yun. The "breaking" and "establishing" of teachers' evaluation reform in universities—analysis framework based on new public service theory[J]. Modern Education Management, 202, (8): 99-107.
[2]	黄春晨, 鲁长风, 田友谊. 人工智能赋能高等教育的政策嬗变与展望——基于“主题-工具-评价”的三维分析框架[J]. 高教探索, 2025(1): 48-59.
	Huang Chun-chen, Lu Chang-feng, Tian You-yi. Policy transformation and future prospects of artificial intelligence empowering higher education[J]. Higher Education Exploration, 2025 (1): 48-59.
[3]	常耀成, 张宇翔, 王红, 等. 特征驱动的关键词提取算法综述[J]. 软件学报, 2018, 29(7): 2046-2070.
	Chang Yao-cheng, Zhang Yu-xiang, Wang Hong, et al. Features oriented survey of state-of-the-art keyphrase extraction algorithms[J]. Journal of Software, 2018, 29(7): 2046-2070.
[4]	刘静, 徐学, 蔺跟荣. 现代信息技术赋能高校教师评价改革的实施路径探析[J]. 黑龙江高教研究, 2024, 42(9): 149-153.
	Liu Jing, Xu Xue, Lin Gen-rong. Implementation approaches of modern information technology empowering the teacher evaluation reformin higher education institutions[J]. Heilongjiang Researches on Higher Education, 2024, 42(9): 149-153.
[5]	胡少虎, 张颖怡, 章成志. 关键词提取研究综述[J]. 数据分析与知识发现, 2021, 5(3): 45-59.
	Hu Shao-hu, Zhang Ying-yi, Zhang Cheng-zhi. Review of keyword extraction studies[J]. Data Analysis and Kno- wledge Discovery, 2021, 5(3): 45-59.
[6]	于强, 林民, 李艳玲. 基于深度学习的关键词生成研究综述[J]. 计算机工程与应用, 2022, 58(14): 27-39.
	Yu Qiang, Lin Min, Li Yan-ling. Review of keyphrase generation based on deep learning[J]. Computer Engineering and Applications, 2022, 58(14): 27-39.
[7]	Salton G, Wong A, Yang C S. A vector space model for automatic indexing[J]. Communications of the ACM, 1975, 18(11): 613-620.
[8]	Page L, Brin S, Motwani R, et al. The PageRank citation ranking: bringing order to the web[C]∥The Web Conference,Technical Report, Toronto,Canada,1999:161-172.
[9]	Mihalcea R, Tarau P. Textrank: Bringing order into text[C]∥Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, Barcelona, Spain, 2004: 404-411.
[10]	Bougouin A, Boudin F, Daille B. Topicrank: graph-based topic ranking for keyphrase extraction[C]∥International Joint Conference on Natural Language Processing,Nagoya, Japan, 2013: 543-551.
[11]	Florescu C, Caragea C. Positionrank: an unsupervised approach to keyphrase extraction from scholarly documents[C]∥Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (volume 1: long papers), Vancouver, Canada,2017: 1105-1115.
[12]	Liu Z, Huang W, Zheng Y, et al. Automatic keyphrase extraction via topic decomposition[C]∥Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, Cambridge, USA,2010: 366-376.
[13]	Sterckx L, Demeester T, Deleu J, et al. Topical word importance for fast keyphrase extraction[C]∥ Proceedings of the 24th International Conference on World Wide Web,Florence, Italy, 2015: 121-122.
[14]	Wan X, Xiao J. Single document keyphrase extraction using neighborhood knowledge[C]∥Proceedings of the AAAI Conference on Artificial Intelligence,San Diego, USA, 2008, 8: 855-860.
[15]	Bennani-Smires K, Musat C, Hossmann A, et al. Simple unsupervised keyphrase extraction using sentence embeddings[J/OL].[2025-02-26].arXiv preprint arXiv:.
[16]	Campos R, Mangaravite V, Pasquali A, et al. Yake! collection-independent automatic keyword extractor[C]∥Proceedings of the European Conference on Information Retrieval, Grenoble, France, 2018: 806-810.
[17]	李渊本. 正则函数在统计机关人事信息数据清洗中的应用[J]. 统计与咨询, 2024(6): 36-38.
	Li Yuan-ben. Application of regular expressions in data cleaning of statistical agency human resource information[J]. Statistics and Consultation, 2024(6): 36-38.
[18]	周宁,石雯茜,朱昭昭. 基于粗糙数据推理的TextRank关键词提取算法[J]. 中文信息学报, 2020, 34(9): 44-52.
	Zhou Ning, Shi Wen-qian, Zhu Zhao-zhao. TextRank keyword extraction algorithm based on rough data-deduction[J]. Journal of Chinese Information Pro- cessing, 2020, 34(9): 44-52.
[19]	丁晓阳,王兰成. 网络论坛文本特征词权重计算优化方法研究[J]. 情报理论与实践, 2021, 44(5): 187-192.
	Ding Xiao-yang, Wang Lan-cheng. Research on opti- mized calculation method for weight of terms in BBS text[J]. Information Studies: Theory & Application, 2021, 44(5): 187-192.
[20]	祖弦,谢飞. 一种基于全局和局部特征表示的关键词抽取算法[J]. 云南大学学报:自然科学版, 2023, 45(4): 825-836.
	Zu Xian, Xie Fei. A keyphrase extraction algorithm based on global and local feature representation[J]. Journal of Yunnan University(Natural Sciences Edition), 2023, 45(4): 825-836.
[21]	焦宇超, 阎刚. 基于BERT与要素提取的相似案例匹配[J]. 智能计算机与应用, 2025, 15(1): 130-135.
	Jiao Yu-chao, Yan Gang. Similar case matching based on BERT and feature extraction[J]. Intelligent Computer and Applications, 2025, 15(1): 130-135.
[22]	袁家政, 须德, 鲍泓. 基于结构与文本关键词相关度的XML网页分类研究[J]. 计算机研究与发展, 2006,43 (8): 1361-1367.
	Yuan Jia-zheng, Xu De, Bao Hong. An efficient XML documents classification method based on structure and keywords frequency[J]. Journal of Computer Research and Development, 2006, 43(8): 1361-1367.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

方法	F₁@1	F₁@3	F₁@5	F₁@10
文献［7］	6.03	15.73	24.70	41.57
文献［11］	7.27	19.76	29.64	48.05
文献［12］	8.91	23.95	33.71	50.71
文献［13］	7.42	21.08	32.11	50.70
文献［15］	6.79	15.64	22.68	34.79
本文	10.08	24.14	34.56	51.37

方法	人文学部	社会科学学部	理学部	工学部	信息科学学部
文献［7］	56.12	55.84	58.83	54.25	56.78
文献［11］	64.31	63.19	64.81	62.73	63.14
文献［12］	62.01	62.19	65.29	59.13	61.40
文献［13］	62.53	63.06	65.48	59.92	61.05
文献［15］	51.11	52.00	57.81	47.90	52.30
本文	66.44	64.06	67.49	64.13	63.20

窗口大小	F₁@1	F₁@3	F₁@5	F₁@10	平均值
1	7.14	19.24	30.21	48.89	26.37
2	8.11	21.10	31.04	49.88	27.53
4	9.32	21.85	31.57	50.34	28.27
6	10.08	24.14	34.56	51.37	30.04
8	7.92	21.11	31.40	50.49	27.73
10	7.98	20.52	31.17	49.86	27.38

基于改进PositionRank算法的高校教师自我评价关键词提取方法

Keyword extraction method for university faculty self-evaluations based on the improved PositionRank algorithm

RICH HTML

PDF (PC)

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 22

相关文章 2

Metrics

本文评价

推荐阅读 0

[1]	龚勃文^1,2,林赐云^1,2,李静³,杨兆升^1,2. 基于核自组织映射-前馈神经网络的交通流短时预测[J]. 吉林大学学报(工学版), 2011, 41(4): 938-943.
[2]	张明国，耿云海，贾琳恒 . 基于RBF网络上界自适应学习的预警卫星滑模控制[J]. 吉林大学学报(工学版), 2007, 37(04): 959-964.