共查询到20条相似文献，搜索用时 22 毫秒
1.
《Information processing & management》2020,57(2):102168
Citation analysis does not tell the whole story about the innovativeness of scientific papers. Works by prominent authors tend to receive disproportionately many citations, while publications by less well-known researchers covering the same topics may not attract as much attention. In this paper we address the shortcomings of traditional scientometric approaches by proposing a novel method that utilizes a classifier for predicting publication years based on latent topic distributions. We then calculate real-number innovation scores used to identify potential breakthrough papers and turnaround years. The proposed approach can complement existing citation-based measures of article importance and author contribution analysis; it opens as well novel research direction for time-based, innovation-centered research scientific output evaluation. In our experiments, we focus on two corpora of research papers published over several decades at two well-established conferences: The World Wide Web Conference (WWW) and the International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), containing around 3500 documents in total. We indicate significant years and demonstrate examples of highly-ranked papers, thus providing a novel insight on the evolution of the two conferences. Finally, we compare our results to citation analysis and discuss how our approach may complement traditional scientometrics. 相似文献
2.
3.
In this work we develop new journal classification methods based on the h-index. The introduction of the h-index for research evaluation has attracted much attention in the bibliometric study and research quality evaluation. The main purpose of using an h-index is to compare the index for different research units (e.g. researchers, journals, etc.) to differentiate their research performance. However the h-index is defined by only comparing citations counts of one’s own publications, it is doubtful that the h index alone should be used for reliable comparisons among different research units, like researchers or journals. In this paper we propose a new global h-index (Gh-index), where the publications in the core are selected in comparison with all the publications of the units to be evaluated. Furthermore, we introduce some variants of the Gh-index to address the issue of discrimination power. We show that together with the original h-index, they can be used to evaluate and classify academic journals with some distinct advantages, in particular that they can produce an automatic classification into a number of categories without arbitrary cut-off points. We then carry out an empirical study for classification of operations research and management science (OR/MS) journals using this index, and compare it with other well-known journal ranking results such as the Association of Business Schools (ABS) Journal Quality Guide and the Committee of Professors in OR (COPIOR) ranking lists. 相似文献
4.
《Information processing & management》2020,57(4):102240
Multi-label classification (MLC) has attracted many researchers in the field of machine learning as it has a straightforward problem statement with varied solution approaches. Multi-label classifiers predict multiple labels for a single instance. The problem becomes challenging with the increasing number of features, especially when there are many features and labels which depend on each other. It requires dimensionality reduction before applying any multi-label learning method. This paper introduces a method named FS-MLC (Feature Selection forMulti-Label classification using Clustering in feature-space). It is a wrapper feature selection method that uses clustering to find the similarity among features and example-based precision and recall as the metrics for feature rankings to improve the performance of the associated classifier in terms of sample-based measures. First, clusters are created for features considering them as instances then features from different clusters are selected as the representative of all the features for that cluster. It reduces the number of features as a single feature represents multiple features within a cluster. It neither requires any parameter tuning nor the user threshold for the number of features selected. Extensive experimentation is performed to evaluate the efficacy of these reduced features using nine benchmark MLC datasets on twelve performance measures. The results show an impressive improvement in terms of sample-based precision, recall, and f1-score with up to 23%-93% discarded features. 相似文献
5.
《Information processing & management》2022,59(5):103053
As a well-known multi-label classification method, the performance of ML-KNN may be affected by the uncertainty knowledge from samples. The rough set theory acts as an effective tool for data uncertainty analysis, which can identify the samples easy to cause misclassification in the learning process. In this paper, a hybrid framework by fusing rough sets with ML-KNN for multi-label learning is proposed, whose main idea is to depict easy misclassified samples by rough sets and to measure the discernibility of attributes for such samples. First, a rough set model titled NRFD_RS based on neighborhood relations and fuzzy decisions is proposed for multi-label data to find the heterogeneous sample pairs generated from the boundary regions of each label. Then, the weight of an attribute is defined by evaluating its discernibility to those heterogeneous sample pairs. Finally, a weighted HEOM distance is reconstructed and utilized to ML-KNN. Comprehensive experimental results with fourteen public multi-label data sets, including ten regular-scale and four larger-scale data sets, verify the effectiveness of the proposed framework relative to several state-of-the-art multi-label classification methods. 相似文献
6.
《Information processing & management》2023,60(3):103320
We propose a CNN-BiLSTM-Attention classifier to classify online short messages in Chinese posted by users on government web portals, so that a message can be directed to one or more government offices. Our model leverages every bit of information to carry out multi-label classification, to make use of different hierarchical text features and the labels information. In particular, our designed method extracts label meaning, the CNN layer extracts local semantic features of the texts, the BiLSTM layer fuses the contextual features of the texts and the local semantic features, and the attention layer selects the most relevant features for each label. We evaluate our model on two public large corpuses, and our high-quality handcraft e-government multi-label dataset, which is constructed by the text annotation tool doccano and consists of 29920 data points. Experimental results show that our proposed method is effective under common multi-label evaluation metrics, achieving micro-f1 of 77.22%, 84.42%, 87.52%, and marco-f1 of 77.68%, 73.37%, 83.57% on these three datasets respectively, confirming that our classifier is robust. We conduct ablation study to evaluate our label embedding method and attention mechanism. Moreover, case study on our handcraft e-government multi-label dataset verifies that our model integrates all types of semantic information of short messages based on different labels to achieve text classification. 相似文献
7.
随着学术研究的日益规范化和复杂化，合作成为增加科研产出的主要途径。本文通过问卷收集了主要院校的科研评价制度，将其与三大经济管理类期刊的论文发表数据进行匹配，基于2000-2014年间部分高校调整第一作者制度的准自然实验，采用双重差分法（DID）的设计考察了科研制度对论文合作的影响。研究发现：（1）评职称认可非第一作者的制度能够使得论文合作的概率显著提高约33.5%，而评奖励承认非第一作者的制度没有显著影响；（2）在考虑了合作的异质性后，非第一作者制度主要促进了跨校合作，对院内合作和同校跨院合作的影响不明显；（3）作用机制分析表明，这种合作效应主要源自教师面临的晋升压力。本文的结论对于推动科研评价体系改革具有重要参考价值。 相似文献
8.
Indicators for complex innovation systems 总被引：3，自引：0，他引：3
J. Sylvan Katz 《Research Policy》2006,35(7):893-909
Performance indicators such as national wealth (GDP per capita), R&D intensity (GERD/GDP) and scientific impact (citations/paper) are used to compare innovation systems. These indicators are derived from the ratio of primary measures such as population, GDP, GERD and papers. Frequently they are used to rank members of an innovation system and to inform decision makers. This is illustrated by the European Research Area S&T indicators scoreboard used to compare the performance of member states.A formal study of complex systems has evolved over the past few decades from common observations made by researchers from many fields. Complex systems are dynamic and many of their properties emerge from the interactions among the entities in them. They also have a propensity to exhibit power law or scaling correlations between primary measures used to characterize them.Katz [Katz, J.S., 2000. Scale independent indicators and research assessment. Science and Public Policy 27, 23-36] showed that scientific impact (citations/paper) scales with the size of the group (papers). In this paper it will be shown that two other common measures, R&D intensity and national wealth, scale with the sizes of European countries and Canadian provinces. Some of these scaling correlations are predictable. These findings illustrate that a performance indicator derived from the ratio of two measures may not be properly normalized for size.This paper argues that innovation systems are complex systems. Hence scaling correlations are expected to exist between the primary measures used to characterize them. These scaling correlations can be used to construct scale-independent (scale-adjusted) indicators and models that are truly normalized for size. Scale-independent indicators can more accurately inform decision makers how groups of different sizes contribute to an innovation system. The ranks of member groups of an innovation system by scale-independent indicators can be subtly and profoundly different than the ranks given by conventional indicators. The differences can result in a shift in perspective about the performance of members of an innovation system that has public policy implications. 相似文献
9.
【目的/意义】由于自媒体平台中的多标签文本具有高维性和不平衡性,导致文本分类效果较差,因此通过
研究5G环境下高校图书馆自媒体平台多标签文本分类方法对解决该问题具有重要意义。【方法/过程】本文首先通
过对采集的5G环境下高校图书馆自媒体平台多标签文本进行预处理,包括无意义数据去除、文本分词以及去停用
词等;然后采用改进主成分分析方法进行多标签文本降维处理,利用向量空间模型实现文本平衡化处理;最后以处
理后的文本为基础,采用Adaboost和SVM两种算法构建文本分类器,实现多标签文本分类。【结果/结论】实验结果
表明,本文拟定的自媒体平台标签文本分类方法可以使汉明损失降低,F1值提高,多标签文本分类效果好,且耗时
较低,具有可靠性。【创新/局限】由于本研究中的数据集数量不够多,所以在测试和验证方面,得出的结果具有一定
局限性。因此在未来研究中期望利用更为丰富的数据库,对所设计的方法做出进一步的改进与创新。 相似文献
10.
《Information processing & management》2022,59(5):103028
Assigning paper to suitable reviewers is of great significance to ensure the accuracy and fairness of peer review results. In the past three decades, many researchers have made a wealth of achievements on the reviewer assignment problem (RAP). In this survey, we provide a comprehensive review of the primary research achievements on reviewer assignment algorithm from 1992 to 2022. Specially, this survey first discusses the background and necessity of automatic reviewer assignment, and then systematically summarize the existing research work from three aspects, i.e., construction of candidate reviewer database, computation of matching degree between reviewers and papers, and reviewer assignment optimization algorithm, with objective comments on the advantages and disadvantages of the current algorithms. Afterwards, the evaluation metrics and datasets of reviewer assignment algorithm are summarized. To conclude, we prospect the potential research directions of RAP. Since there are few comprehensive survey papers on reviewer assignment algorithm in the past ten years, this survey can serve as a valuable reference for the related researchers and peer review organizers. 相似文献
11.
目前,我国高校在科技评价中,普遍存在“注重数量、看轻质量”的问题,对科研成果、科技人员的不恰当的量化评价,并与利益挂钩,导致科研成果与社会的实际发展需求无法紧密的联系起来。尤其对于行业特色高校,行业背景浓厚,对科技成果的应用性要求较高,所以对于成果实际应用的考察应该成为行业特色高校科技评价指标中的关键部分。针对上述问题,本文对具有行业特色的高校科技分类评价开展了探索与研究。首先分析了当前科技评价的现状,探讨了当前行业特色高校科技评价的不足之处;然后基于科技评价的现状,本文提出了科技评价的三大基本原则：坚持分类评价、建立高效评价机制和建立特色评价体系。最后引入了灰色理论,研究了行业特色高校的科技评价模型,并且针对行业特色高校的特点,重点确定了分类评价指标,提出了关于行业应用、学术成绩和行业指导这3个方面共19项分类评价指标,同时提出借鉴英美等国家比较成熟的科技评价体系来完善我国行业特色高校分类评价的观点。 相似文献
12.
Popular and/or prestigious? Measures of scholarly esteem 总被引：1，自引：0，他引：1
Citation analysis does not generally take the quality of citations into account: all citations are weighted equally irrespective of source. However, a scholar may be highly cited but not highly regarded: popularity and prestige are not identical measures of esteem. In this study we define popularity as the number of times an author is cited and prestige as the number of times an author is cited by highly cited papers. Information retrieval (IR) is the test field. We compare the 40 leading researchers in terms of their popularity and prestige over time. Some authors are ranked high on prestige but not on popularity, while others are ranked high on popularity but not on prestige. We also relate measures of popularity and prestige to date of Ph.D. award, number of key publications, organizational affiliation, receipt of prizes/honors, and gender. 相似文献
13.
Ran Wang Robert Ridley Xi’ao Su Weiguang Qu Xinyu Dai 《Information processing & management》2021,58(2):102441
The aim in multi-label text classification is to assign a set of labels to a given document. Previous classifier-chain and sequence-to-sequence models have been shown to have a powerful ability to capture label correlations. However, they rely heavily on the label order, while labels in multi-label data are essentially an unordered set. The performance of these approaches is therefore highly variable depending on the order in which the labels are arranged. To avoid being dependent on label order, we design a reasoning-based algorithm named Multi-Label Reasoner (ML-Reasoner) for multi-label classification. ML-Reasoner employs a binary classifier to predict all labels simultaneously and applies a novel iterative reasoning mechanism to effectively utilize the inter-label information, where each instance of reasoning takes the previously predicted likelihoods for all labels as additional input. This approach is able to utilize information between labels, while avoiding the issue of label-order sensitivity. Extensive experiments demonstrate that our method outperforms state-of-the art approaches on the challenging AAPD dataset. We also apply our reasoning module to a variety of strong neural-based base models and show that it is able to boost performance significantly in each case. 相似文献
14.
《Information processing & management》2023,60(4):103384
As the most ecologically active cryptocurrency platform, Ethereum has attracted the attention of many researchers. Leveraging its fully public transaction data, most existing analysis models all account interactions as a network and explores it from a static and global perspective. However, their work ignored the investigation of dynamic and microscopic features of accounts. Therefore, we conduct the first work about these features of different kinds of accounts on Ethereum. We select six account types on Ethereum, including exchanges, phishing, etc. Then we characterize and compare the dynamics of their transactions. Next, we construct a transaction ego network for each account, and investigate the network features from the perspective of microscopic structure. Experimental results show that different kinds of accounts have their own traits in terms of transaction features and properties of ego networks, which greatly contributes to understanding their roles. Additionally, there are obvious differences between normal accounts and illegal accounts in some characteristics such as transaction neighbors and interaction patterns. Moreover, we observe that criminal gangs may be participating in phishing scams. Finally, based on the conclusions of the account analysis, we design a variety of account features and use them for the account classification task. The experimental results prove that the dynamic and microscopic features we proposed are beneficial to distinguish different types of accounts. We believe our research can provide reference value for account classification tasks in Ethereum and other blockchains. 相似文献
15.
研究影响评价是一个跨学科新领域,欧美等国家和地区的政府机构与研究组织已将其作为科学决策的实用工具.着眼于医学领域,对国际上研究影响的定义、评价框架、影响分类和评价指标以及评价方法进行总结,发现国际上通常使用混合方法来评价医学研究影响,包括文献计量、同行评议、案例研究和经济学分析等,但需要采用利益相关者访谈验证自制评价框架的有效性;同时目前尚未形成统一、最佳的研究影响框架,影响归因有难度.最后结合实际,为我国医学研究影响评价的理论与实践发展提出对策建议:科技评价范式由绩效评价转向影响评价;提高科研人员创造、捕捉研究影响的能力;开展符合中国国情的相关理论研究;构建资源库以提供数据支撑等. 相似文献
16.
17.
现有的学术论文评价方法主要采用发文期刊的影响因子、发表后的被引用次数等作为评价指标,无法全面展现学术论文的内容价值。文章在系统分析论文评价方法特点与不足的基础上,以Bates的Berrypicking模型为理论基础,提出了以学术大众为主体开展论文质量评价的思路。通过分析大众评价的可行性,构建出学术论文大众评价的指标体系,并对论文评级、价值类型、专家意见、大众评语等大众指标和权威指标的内涵进行了解释。 相似文献
18.
基于科学计量学的我国科学论文产出分析 总被引：2，自引：0，他引：2
运用科学计量学方法,统计美国科学信息所（ISI）提供的数据,对我国的科学研究成果进行定量分析和国际比较,从而来评价我国当前的科学研究现状．结果表明,我国的SCI、SSCI论文呈指数增长,高引文数量虽有增长,但增长速度远远不及论文数量增长的速度,而且中国内地高校院所入围Highlycited．CON高引研究人员名单的数目仅为3人,这从一个侧面反映了我国科学研究机制在经费投入、政策导向、人才培养方面存在着不足． 相似文献
19.
本文采用事件史分析方法（EHA）探讨导师身份等因素对我国科研人员职业成长的影响。Cox比例风险模型结果表明,导师行政地位对晋升正高职称具有正向促进作用,而导师学术地位未能对晋升副高、正高职称产生显著影响;导师身份类型为双高型和高低兼具型的科研人员比导师身份为双低型的科研人员晋升正高职称更快,即导师身份类型层次越高,科研人员晋升正高职称速度越快。此外,研究结果还发现,科研能力是实现科研职称晋升的基础因素和必要条件,在985高校工作延缓了晋升正高职称速度,具有博士后经历有利于晋升正高职称,男性科研人员更容易实现职称晋升。 相似文献
20.
近年来跨学科研究已成为基础研究发展的重要趋势和方向。本文基于Web of Science核心数据库,运用文献计量方法和社会网络分析法对比分析了2003-2017年间中国、美国、日本国际论文的跨学科特点和发展态势,研究内容包括跨学科论文产出特征、学科多样性、学科融合网络特征和主要学科融合组合。结果显示,我国跨学科论文绝对数量的增长速度高于美国和日本;与美国和日本不同的是,跨学科论文中跨学部论文的比例中国近几年呈下降趋势。中、美、日都以两个学科融合为主,尽管两个以上学科融合的比例中国高于美国和日本,但学科融合网络特征显示,中国学科融合网络的连通性、凝聚性和平均度数都要低于美国和日本。中、美、日主要的学科融合组合存在差异,工程学部在我国跨学科研究中占有重要地位。 相似文献