|
|
|
| A Method of Search Term Recommendation Based on Dependency Syntactic Network Combined with PageRank |
| Lou Wen1,2,3, Ma Xinyu1, Su Zilong1 |
1.Department of Information Management, School of Economics and Management, East China Normal University, Shanghai 200062
2.Institute for Academic Evaluation and Development in East China Normal University, Shanghai 200241
3.Key Laboratory of Advanced Theory and Application in Statistics and Data Science (East China Normal University), Ministry of Education, Shanghai 200062 |
|
|
|
|
Abstract Facing increasing information overload and the rise of cross-cutting research, studies on the filtering ability of the information retrieval system to provide effective search term recommendation services are becoming increasingly important. This study proposes a search term recommendation method that integrates dependent syntax and language network theories using the PageRank algorithm. By constructing a search term set and dependent syntax network, and sorting the search terms using the PageRank algorithm, the search term recommendation is realized. The method is validated using the Web of Science platform 124,516 literature abstracts in the field of information science & library science as an example. We also invited ten MLIS graduate students to participate in the user study, which combined the comparison results with similar methods and systems. The results show that the accuracy of the recommended method is 80%, average Cosine similarity in the recommendation list is 0.53, and average Jaccard similarity in the table is 0.39. Compared with other methods and systems, the diversity of our approach reacts better with a higher degree of surprise. Overall, the results show that our method increased the coverage of the search terms based on the user’s information requirements. Our method is expected to provide references on methodological perspectives on the representation of information retrieval. It can be directly applied for terminological organization in the back end of information retrieval, as well as indirectly for knowledge discovery and inter-disciplinary study.
|
|
Received: 02 January 2023
|
|
|
|
1 宋艳辉, 朱李, 舒非, 等. 中美图情学博士学位论文主题跨学科发展比较研究[J]. 情报学报, 2022, 41(5): 536-548.
2 熊文靓, 付慧真. 基于主题挖掘模型的跨学科性研究主题及其演化研究[J]. 情报科学, 2021, 39(11): 117-126.
3 崔育宝, 李金龙, 张淑林. 交叉学科建设: 内涵论析、实施困境与推进策略[J]. 中国高教研究, 2022(4): 16-22.
4 汪东芳, 曹燕, 曾文. 面向科技查新的词表构建研究[J]. 图书馆学研究, 2020(19): 50-57.
5 张海涛, 张枭慧, 魏萍, 等. 网络用户信息检索行为研究进展[J]. 情报科学, 2020, 38(5): 169-176.
6 张海涛, 徐海玲, 张枭慧, 等. 国内外图书情报领域用户画像研究现状及展望[J]. 图书情报工作, 2019, 63(7): 127-134.
7 汤志康, 李春英, 汤庸, 等. 学术社交平台论文推荐方法[J]. 计算机与数字工程, 2017, 45(2): 221-225.
8 郭佳, 黄程松. 国外网络环境中信息过载研究进展[J]. 情报科学, 2018, 36(7): 170-176.
9 肖丽平, 娄策群. 互联网发展环境下“信息超限”问题研究[J]. 图书馆学研究, 2018(10): 16-21, 29.
10 赵怿怡, 刘海涛. 基于网络观的语言研究[J]. 厦门大学学报(哲学社会科学版), 2014(6): 127-136.
11 刘知远, 郑亚斌, 孙茂松. 汉语依存句法网络的复杂网络性质[J]. 复杂系统与复杂性科学, 2008, 5(2): 37-45.
12 Ren Z Y, Peng B, Schleyer T K, et al. Hybrid collaborative filtering methods for recommending search terms to clinicians[J]. Journal of Biomedical Informatics, 2021, 113: 103635.
13 赵俊逸, 庄福振, 敖翔, 等. 协同过滤推荐系统综述[J]. 信息安全学报, 2021, 6(5): 17-34.
14 纪文璐, 王海龙, 苏贵斌, 等. 基于关联规则算法的推荐方法研究综述[J]. 计算机工程与应用, 2020, 56(22): 33-41.
15 范圆圆, 王曰芬. 基于学术社交网络用户关系的文献搜索推荐研究[J]. 现代情报, 2021, 41(9): 32-39.
16 张洋, 高艳华, 郭晓坤. 使用关联检索缓和推荐系统中的稀疏性问题[J]. 计算机仿真, 2021, 38(9): 495-500.
17 Nair A M, Benny O, George J. Content based scientific article recommendation system using deep learning technique[C]// Proceedings of ICISC 2021: Inventive Systems and Control. Singapore: Springer, 2021: 965-977.
18 魏玲, 郭新悦. 融合用户画像与协同过滤的知识付费平台个性化推荐模型[J]. 情报理论与实践, 2021, 44(3): 188-193.
19 贾凡, 康舒雅, 江为强, 等. 基于相似性的多用户漏洞推荐算法[J]. 清华大学学报(自然科学版), 2023, 63(9): 1399-1407.
20 Osadchiy T, Poliakov I, Olivier P, et al. Recommender system based on pairwise association rules[J]. Expert Systems with Applications, 2019, 115: 535-542.
21 郭伟光. 基于农产品本体的语义检索推荐系统框架[J]. 电脑知识与技术, 2019, 15(17): 191-193.
22 熊回香, 李晓敏, 杜瑾. 基于学术关键词与共被引的学者推荐研究[J]. 情报学报, 2021, 40(7): 725-733.
23 杨辰, 刘婷婷, 刘雷, 等. 融合语义和社交特征的电子文献资源推荐方法研究[J]. 情报学报, 2019, 38(6): 632-640.
24 熊回香, 孟璇, 叶佳鑫. 基于关键词语义类型和文献老化的学术论文推荐[J]. 现代情报, 2021, 41(1): 13-23.
25 丁浩, 胡广伟, 齐江蕾, 等. 基于随机森林和关键词查询扩展的医学文献推荐方法[J]. 数据分析与知识发现, 2022, 6(7): 32-43.
26 袁仁进, 陈刚, 李锋, 等. 基于VSM和Bisecting k-means聚类的新闻推荐方法[J]. 北京邮电大学学报, 2019, 42(1): 114-119.
27 Andra D, Baizal A B. E-commerce recommender system using PCA and k-means clustering[J]. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 2022, 6(1): 57-63.
28 聂永丹, 王斌, 张岩. 基于改进PageRank算法的文献相关度排序方法[J]. 吉林大学学报(信息科学版), 2022, 40(3): 464-470.
29 Page L, Brin S, Motwani R, et al. The PageRank citation ranking: bringing order to the Web[R]. Palo Alto: Stanford University, 1999: 1-14.
30 王丹. 基于PageRank改进的文献排名算法研究[J]. 计算机时代, 2019(1): 59-62, 66.
31 张勇, 杨赛军, 黄华. CiteRank算法在文献多指标排序中的应用[J]. 中国科技资源导刊, 2021, 53(4): 32-37.
32 华一雄, 张执南. 基于文本相似度和入出比的改进PageRank科研文献搜索方法[J]. 机械设计与研究, 2021, 37(1): 6-9.
33 常家伟, 戴牡红. 基于PageRank和谱方法的个性化推荐算法[J]. 计算机科学, 2018, 45(S2): 398-401.
34 Brin S, Page L. The anatomy of a large-scale hypertextual Web search engine[J]. Computer Networks and ISDN Systems, 1998, 30(1-7): 107-117.
35 Hadhiatma A, Azhari A, Suyanto Y. A scientific paper recommendation framework based on multi-topic communities and modified PageRank[J]. IEEE Access, 2023, 11: 25303-25317.
36 王子茹, 宋尚文, 阎红灿. 协同过滤推荐算法的性能对比与分析[J]. 计算机仿真, 2022, 39(9): 435-440.
37 宁泽飞, 孙静宇, 王欣娟. 基于知识图谱和标签感知的推荐算法[J]. 计算机科学, 2021, 48(11): 192-198.
38 温有奎. 信息检索系统的关联关键词推荐研究[J]. 数字图书馆论坛, 2016(4): 11-14.
39 刘军, 杨军, 宋姗姗. 基于用户购买意愿力的协同过滤推荐算法[J]. 吉林大学学报(理学版), 2021, 59(6): 1432-1438.
40 Liu G G. An ecommerce recommendation algorithm based on link prediction[J]. Alexandria Engineering Journal, 2022, 61(1): 905-910.
41 AricHagberg, DanSchult, PieterSwart. NetworkX reference[DB/OL]. [2018-01-22]. https://networkx.github.io/documentation/stable/_downloads/networkx_reference.pdf.
42 李航. 统计学习方法[M]. 2版. 北京: 清华大学出版社, 2019.
43 汪志伟, 邹艳妮, 吴舒霞. PageRank算法应用在文献检索排序中的研究及改进[J]. 情报理论与实践, 2016, 39(11): 126-130, 144.
44 王春才, 邢晖, 李英韬. 推荐系统评测方法和指标分析[J]. 信息技术与标准化, 2015(7): 27-29, 44.
45 黄泽明. 基于主题模型的学术论文推荐系统研究[D]. 大连: 大连海事大学, 2013. |
|
|
|
