A novel personality detection method based on high-dimensional psycholinguistic features and improved distributed Gray Wolf Optimizer for feature selection     

《Information processing & management》2023,60(2):103217

Existing personality detection methods based on user-generated text have two major limitations. First, they rely too much on pre-trained language models to ignore the sentiment information in psycholinguistic features. Secondly, they have no consensus on the psycholinguistic feature selection, resulting in the insufficient analysis of sentiment information. To tackle these issues, we propose a novel personality detection method based on high-dimensional psycholinguistic features and improved distributed Gray Wolf Optimizer (GWO) for feature selection (IDGWOFS). Specifically, we introduced the Gaussian Chaos Map-based initialization and neighbor search strategy into the original GWO to improve the performance of feature selection. To eliminate the bias generated when using mutual information to select features, we adopt symmetric uncertainty (SU) instead of mutual information as the evaluation for correlation and redundancy to construct the fitness function, which can balance the correlation between features–labels and the redundancy between features–features. Finally, we improve the common Spark-based parallelization design of GWO by parallelizing only the fitness computation steps to improve the efficiency of IDGWOFS. The experiments indicate that our proposed method obtains average accuracy improvements of 3.81% and 2.19%, and average F1 improvements of 5.17% and 5.8% on Essays and Kaggle MBTI dataset, respectively. Furthermore, IDGWOFS has good convergence and scalability.  相似文献   

灰色预测法在情报研究中的应用研究综述     

张晶晶  李泽霞 《图书情报工作》2021,64(24):106-114

[目的/意义] 灰色预测法可有效处理情报研究中广泛存在的小样本数据，通过对灰色预测法在情报研究中的应用情况进行梳理，总结其在应用过程中存在的不足，为灰色预测法在情报研究中的进一步应用提供参考。[方法/过程] 通过综述情报研究中涉及灰色预测法的相关文献，从数据选取、模型构建和解决的问题等方面对情报研究中灰色预测法的应用进行概述，总结当前情报研究中灰色预测法的应用所存在的问题，并提出改进建议。[结果/结论] 在方法应用上，已有研究主要采用数列灰预测，且模型集中在单变量灰色预测模型，根据预测对象不同，灰色预测法已经在包括期刊分析、图书馆运行管理、热点主题分析及科研机构评价方面得到了很好的应用，未来可根据预测对象特点及研究目标尝试不同的灰色预测方法，扩宽灰色预测法在其他方面的情报研究问题中的应用。  相似文献   

Word sense disambiguation based on context selection using knowledge-based word similarity     

Sunjae Kwon  Dongsuk Oh  Youngjoong Ko 《Information processing & management》2021,58(4):102551

In this paper, we introduce a novel knowledge-based word-sense disambiguation (WSD) system. In particular, the main goal of our research is to find an effective way to filter out unnecessary information by using word similarity. For this, we adopt two methods in our WSD system. First, we propose a novel encoding method for word vector representation by considering the graphical semantic relationships from the lexical knowledge bases, and the word vector representation is utilized to determine the word similarity in our WSD system. Second, we present an effective method for extracting the contextual words from a text for analyzing an ambiguous word based on word similarity. The results demonstrate that the suggested methods significantly enhance the baseline WSD performance in all corpora. In particular, the performance on nouns is similar to those of the state-of-the-art knowledge-based WSD models, and the performance on verbs surpasses that of the existing knowledge-based WSD models.  相似文献   

Finding the missing Einsteins: Expanding the breadth of cognitive and noncognitive measures used in academic services     

《Contemporary educational psychology》2020

Education researchers, policymakers, and practitioners are concerned with identifying and developing talent for students with fewer opportunities, especially students from historically marginalized groups. An emerging body of research suggests “universally screening” or testing all students, then matching those students with appropriate educational challenges, is effective in helping marginalized students. However, most tests have focused on two areas: math and verbal reasoning. We leverage three nationally representative samples of the U.S. population at different time points that include both novel cognitive measures (e.g., spatial, mechanical, and abstract reasoning) and non-cognitive measures (e.g., conscientiousness, creativity or word fluency, leadership skill, and artistic skill) to uncover which measures would improve proportional representation of marginalized groups in talent identification procedures. We find that adding spatial reasoning measures in particular—as well as other non-cognitive measures such as conscientiousness, leadership, and creativity—are worthwhile to consider for universal screening procedures for students to narrow achievement gaps at every level of education, including for gifted students. By showing that these nontraditional measures both improve proportional representation of underrepresented groups and have reasonable predictive validity, we also broaden the definition of what it means to be “gifted” and expand opportunities for students from historically marginalized groups.  相似文献   

跨项选材视角下《运动选材学》通用教材不同版本的比较研究     

龙斌  王家辉  王三保 《武汉体育学院学报》2019,53(6):72-78

运用文献资料法、数理统计法和逻辑分析法，对《运动选材学》通用教材不同版本的整体结构内容、章节进行纵横竞技体育历史分析，从跨项选材视角下研究《运动选材学》教材体系的发展规律、历史地位、内容体系存在的问题和建立《运动选材学》内容体系的对策，以期为《运动选材学》教材内容体系的建设与发展提供一些有益的理论依据。同时，也为我国备战2020年东京夏季奥运会和2022年北京冬季奥运会提供一定的理论指导。  相似文献   

Data analysis and feature selection for predictive maintenance: A case-study in the metallurgic industry     

《International Journal of Information Management》2019

Proactive Maintenance practices are becoming more standard in industrial environments, with a direct and profound impact on the competitivity within the sector. These practices demand the continuous monitorization of industrial equipment, which generates extensive amounts of data. This information can be processed into useful knowledge with the use of machine learning algorithms. However, before the algorithms can effectively be applied, the data must go through an exploratory phase: assessing the meaning of the features and to which degree they are redundant. In this paper, we present the findings of the analysis conducted on a real-world dataset from a metallurgic company. A number of data analysis and feature selection methods are employed, uncovering several relationships, which are systematized in a rule-based model, and reducing the feature space from an initial 47-feature dataset to a 32-feature dataset.  相似文献   

Selecting an open innovation community as an alliance partner: Looking for healthy communities and ecosystems     

《Research Policy》2019,48(8):103766

Organizations build strategic alliances with other firms with the intent of tapping into partners’ resources and capturing long-term value from these relationships. Such partnerships are typically governed by contractual or equity arrangements with clear mutual obligations. More recently, however, organizations have begun to seek strategic partnerships with open innovation communities, which are novel digitally enabled forms of organizing, and where contractual commitments are not possible. Thus, selecting the right open innovation community as an alliance partner becomes a more complex decision. We follow how the organizational decision makers, in two technology firms that were pioneers of forming strategic alliances with open innovation communities, developed metrics around making such decisions. We build upon Shah and Swaminathan’s (2008) contingency model of alliance partner selection and consider how it applies to the case of partnering with open innovation communities. This framework was useful in to frame our findings, yet our work recognizes and builds upon two key differences: 1) the evaluation metrics used in selecting an open innovation community were more focused on value creation than value capture; and 2) open ecosystem considerations, and not just partner-specific metrics, featured prominently in this type of alliance partner evaluation. We develop the notions of community and ecosystem health to refer to these new metrics.  相似文献   

图书馆情报学主要研究方法:了解、选择及使用     

储荷婷 《图书情报工作》2019,63(1):146-152

[目的/意义]研究方法在学术研究中发挥着至关重要的作用。确认图书馆情报学领域主要的研究方法，并对它们进行了解熟悉，以在开展研究时能合理选择、灵活使用，确保研究质量。[方法/过程]对近2 000篇图书馆情报学领域的研究文献以及相关研究方法论文进行内容分析，在此基础上对研究方法的类分命名、图书馆情报学界主要的研究方法的确定、特点和使用注意事项进行介绍和讨论。[结果/结论]研究方法应以数据收集法而不是数据分析法命名。图书馆情报学领域常用的研究方法包括实验法、问卷法、理论研讨法、内容分析法、访谈法和书目计量法，每种方法都有各自的特点。因而在选择使用时，既应根据具体研究课题及研究方法之特性，也要考虑使用注意事项，并尽量在同一研究中采用两种或更多的方法，以扬长避短，更有效地展开研究。  相似文献   

知识网络方法在城市产业技术选择中的应用——以北京建设科技创新中心产业技术选择为例     

钮季峰  黄璐  郑文江  葛琴  穆智蕊  陈璐怡 《科技管理研究》2019,39(14)

产业技术选择是城市发展中一项重要的决策内容。传统产业技术选择方法，诸如德尔菲法、层次分析法等，面临着技术分属领域跨度大，颗粒度大小难界定，以及专家主观判断依赖性大的问题。本研究旨在利用知识网络理论，结合文献计量的量化方法，打破传统产业技术选择的局限，帮助城市识别所需的产业技术。本研究以北京的产业技术选择为例，从梳理国家研究机构发布的技术预测结果为起点，筛选与北京城市发展相关度高的产业技术，并结合知识网络理论，量化产业技术在知识网络中的特征参数，并探讨整体网络参数对产业技术选择与政策设计的影响，由此作为城市发展规划中产业选择以及后续产业政策制定的重要参考依据。研究认为，基于知识网络基础的量化方法，在一定程度上解决了现有决策方法偏重定性分析的问题，为城市产业技术选择提供了一种具有科学依据、能够量化评价的分类方法。  相似文献   

我国冬季项目跨界跨项选材研究与启示     

郝月蓉 《河北体育学院学报》2020,34(3):42-46

运用文献资料法和逻辑分析法，对冬季项目跨界跨项选材问题进行辩证分析。认为，2022年北京冬奥会、政府专项政策导向及国内外成功的跨界经验，为我国开展冬季项目跨界跨项选材工作提供了重要的机遇和支持，但跨界跨项选材任务艰巨、冬季项目人才缺口大、运动员培养时间不足、跨界跨项风险大等问题也不容忽视。为进一步做好跨界跨项选材工作，为我国冬季项目持续发展提供充足的人力支持，应积极落实国家政策，做到科学跨选；依托同项群项目选材，跨用传统优势项目人才；抓住冬奥发展机遇，尽快建立完善的人才培养体系。  相似文献