首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献,搜索用时 234 毫秒
1.
微博是一种在线交流形式,以其简短、方便和及时性在中国成为2011年的一个热点.本文以新浪微博为平台,通过抽取2011年7月23日"动车事故"发生后公众发表的微博并进行情感分析.提取了六维情感类(期待,高兴,喜爱,惊讶,焦虑,悲伤,生气和憎恨),构建了用于情感分析的模糊情感本体,建立了微博文本的影响力和情感计算方法,对"动车事故"后的公众情感随事态发展的变化进行了探讨.  相似文献   

2.
基于在线评论的消费者模糊情感计算与推理   总被引:1,自引:0,他引:1  
针对Web 2.0时代大量主观性文本的出现,消费者在线评论描述了消费者关于某一产品或服务的观点或经历。本文基于模糊理论讨论了在线评论中的情感挖掘问题。以消费者心理行为学理论为基础,根据在线评论的自然语言模糊本质属性,建立了消费者心理模糊库群,包括特征、感知、情绪、评价等4个模糊库;结合评论语句的句法分析,给出了消费者态度情感的模糊计算算法(FSCA-OR);并依据消费者的决策过程,进行了推理规则库的构建;最后通过实验验证了所提方法的有效性。  相似文献   

3.
本文从句子级的角度进行了中文文本的情感倾向分析,提出以HowNet中的情感词表为种子情感词集,采用基于CRF模型的半监督学习迭代方法获取大量评价词,然后依据中文词间的语义规则判断句子的极性的方法.将该方法应用于COAE2011中任务2-观点句识别,在评价词的识别和观点句极性判断都取得了很好的结果.  相似文献   

4.
为解决传统的情感分析方法中存在的语义理解能力不足和情感分析不充分问题,本文从语义的角度,运用构建模糊情感本体的方法,对中文在线评论情感分析进行研究.引入情感空间模型,并将传统的在线评论情感分析细分为特征评价和情绪表达两方面.基于已建立的模糊情感本体,对产品(服务)的特征、情感类和强度、程度词、否定词、修辞方法和标点等语义元素进行标注,构建从句子层到文档层的情感计算方法.选取有代表性的评论语料进行实验,结果表明建立的情感分析方法具有优良的准确性和应用性,进一步分析发现不同评论语料中情感具有不同的表达形式和关联关系.  相似文献   

5.
《新闻界》2019,(10):61-71
以女性为主体,经由社交媒体分享性别化的亲身经历而形成"发声文化",使性骚扰、性侵犯成为可见公共议题的在线话语行动,是当下对抗性别不平等权力结构的重要手段。2017年底开始席卷全球的#MeToo运动最为典型。然而,看似轻易的"发声",是当事人与行动者付出大量情感劳动的结果。本文运用文本分析、深度访谈和虚拟民族志等方法,对中国#MeToo运动中的情感管理和情感劳动进行微观分析。研究发现,行动者们对痛苦、恐惧、愤怒和团结感等情感的唤起与抑制共同维系了"发声"的抗争;在权力非对称格局下,行动者们理性地揣摩并遵循情感体制的表达规则,精心构建"发声"文本,以推动反性骚扰/性侵犯在法律和制度层面的变革。中国#MeToo运动具有心理疗愈与社会赋权的双重意义。  相似文献   

6.
基于单句粒度的微博主题挖掘研究   总被引:1,自引:0,他引:1  
针对现有主题挖掘方法的不足,本文提出一种以句子为粒度的微博主题挖掘方法.首先,以标点符号为依据进行微博文本的句子划分,选择名词和动词为特征词来表征句子;其次,以高频特征词在微博文本集中的共现频次为基础构建词语相似矩阵,辅助计算句子相似度,构建句子相似矩阵;然后,以句子相似矩阵为基础进行聚类分析,通过分析聚类结果实现主题发现;最后,利用改进的LexRank算法计算各主题句子的重要度值,组合重要度值高的句子生成主题摘要,以完成对主题的描述.文章通过实验证明了该方法的可行性.  相似文献   

7.
本文提出了一种对中文文本摘要中抽取出的句子进行重述的方法.首先使用基于统计的方法对文本进行特征统计,计算词和句子的权重,摘取出权值较高的句子;然后对这些句子应用一种基于向量相似度计算的算法进行指代消解,同时提出一种新的句子向量相似度的计算方法去除冗余;最后利用启发式规则进行加工,从而得到文本摘要.实验结果显示,系统修改后的文摘具有较好的连贯性和流畅性,与修改之前的文摘相比,文摘质量有明显提高.  相似文献   

8.
史伟  薛广聪  何绍义 《情报学报》2023,(9):1065-1077
针对微博短文本评论,基于情感分析技术,从情感类转移等角度实现对网络舆情演变趋势的预测。本文以突发事件“新冠肺炎疫情”初期的相关微博评论文本作为研究对象,基于扩展关联规则Apriori算法和马尔可夫链提出一种新的方法,即偏差规则马尔可夫模型(the deviation rules Markov model,DRMM)。该模型分析了网民情感类间的相关性和转移性,通过计算不同的情感类转移概率、构建时变的情感状态转移矩阵对疫情初期网民情感状态的变化趋势进行预测。实验采取平均绝对误差(mean absolute error,MAE)和均方根误差(root mean squared error,RMSE)来衡量模型预测值与真实值之间的误差。研究结果表明,该模型具有较好的有效性和准确性,预测值和真实值的拟合效果在预期范围之内。  相似文献   

9.
基于句子相似度的文本主题句提取算法研究   总被引:1,自引:0,他引:1  
文本主题提取是文本挖掘领域的重要研究内容,解决文本信息泛滥的重要手段.为了解决现有文本主题句提取中一些局部主题容易被忽略的问题,本文提出一种"先分割,再提取"的思想.首先将文本表示为句子的线性序列,句子表示为词的线性序列,并对每个句子都预处理为含有实词的词汇链,然后基于知网(Hownet)计算相邻句子相似度.基于句子相似度,采用文本分割技术将文本分为多个关于子主题的句子包,通过句子关系图对这些句子包进行主题句提取.最后选用不同的语料库,设计进行了可接受性测试,实验结果验证该算法是可行、有效地.  相似文献   

10.
文本情感分析作为自然语言处理领域的一个重要分支,被广泛运用于舆情分析和内容推荐等领域,近年来成为研究的热点。提出基于语法规则和自注意力机制的GCN情感分析方法。首先,使用Glo Ve预训练模型与Bi LSTM模型提取文本的语义特征,并采用spa Cy工具对文本进行句法依存分析,从而提取文本的语法规则。其次,引入自注意力机制,并依据语义特征与语法规则构建GCN模型。最后,采用全连接层和Softmax分类器进行情感分类。实验结果表明,该方法与相关基线模型相比,在Twitter数据集上的准确率和宏F1值分别得到了提升,具有较好的情感分类性能。  相似文献   

11.
In the summer of 2013, the United Nations and NBC began a season-long collaborative campaign involving the primetime television series Revolution (2012–2014), a show about the global loss of electricity, to promote the former’s energy resource campaigns. The two entities collaboratively produced various texts and events encouraging audiences to learn more about United Nations energy initiatives and how people throughout the world lack consistent access to electricity. This essay offers a close, rhetorical reading of the collaboration’s paratexts, examining stated responses from actors, creators, interviewers, and panel participants within this content. In particular, I argue that contact between the paratexts and the “formative” text (that of the show’s narrative) can encourage viewers to think about electricity from the perspective of their own material practices, dependencies, and fears over losing the technological world. I examine how these invested viewers interpreted the United Nations’ efforts through such commitments. Naming a fictive world, and its feared loss, as metonymic of energy politics illustrates how meaning, emotion, and texts circulate, while also implicating the use of celebrity platforms for sociopolitical issues such as energy access.  相似文献   

12.
OBJECTIVES: The objective of this study was to identify trends in academic health sciences libraries (AHSLs) as they adapt to the shift from a print knowledgebase to an increasingly digital knowledgebase. This research was funded by the 2003 David A. Kronick Traveling Fellowship. METHODS: The author spent a day and a half interviewing professional staff at each library. The questionnaire used was sent to the directors of each library in advance of the visit, and the directors picked the staff to be interviewed and set up the schedule. RESULTS: Seven significant trends were identified. These trends are part of the shift of AHSLs from being facility and print oriented with a primary focus on their role as repositories of a print-based knowledgebase to a new focus on their role as the center or "nexus" for the organization, access, and use of an increasingly digital-based knowledgebase. CONCLUSION: This paper calls for a national effort to develop a new model or structure for health sciences libraries to more effectively respond to the challenges of access and use of a digital knowledgebase, much the same way the National Library of Medicine did in the 1960s and 1970s in developing and implementing the National Network of Libraries of Medicine. The paper then concludes with some examples or ideas for research to assist in this process.  相似文献   

13.
For e-resource librarians, maintaining e-book and e-journal holdings within electronic resource management systems is a labor intensive and often manual process. In 2014, with the aim of saving library staff valuable time and effort, the Online Computer Library Center, Inc. (OCLC) launched a service to provide automated holdings management within the WorldCat knowledgebase. For a select group of content providers, including some of the largest e-book aggregators, holdings information can be populated and updated automatically within the knowledgebase without intervention from library staff. At the University of Toronto Libraries, we conducted a study to assess the accuracy and efficiency of these automated holdings management services. This presentation outlines the results of the study and provides suggestions for further improvement to the current services offered.  相似文献   

14.
This paper examines the rise of anti-Korean sentiment in contemporary Taiwan particularly at the turn of the 2010s. It moves beyond conceptualizing emotion as psychological status to conceive anti-Korean sentiment as a cultural text that debunks the complexity of emotion as an active agent of collective (un)consciousness. Specifically, the paper considers anti-Korean sentiment in Taiwan as an affective space where young Taiwanese demonstrate their active engagement in (re)locating Taiwan in the global imaginative map and their struggle for national identity in the midst of increasing geopolitical tensions in East Asia. Instead of seeing anti-Korean sentiment from an international relations perspective, this paper studies anti-Korean sentiment from a bottom-up perspective through in-depth interviews with young Taiwanese who are actively engaging with anti-Korean discussions and explore various ways that anti-Korean sentiment mediates and transforms imaginative relations between Taiwan and Korea and beyond.  相似文献   

15.
16.
新时代科技期刊青年编辑要有“三心”“二意”   总被引:1,自引:1,他引:0  
高峻 《编辑学报》2018,30(6):655-657
青年编辑的成长和培养问题是科技期刊编辑界关注的热点。结合新时代要求,对青年编辑应当具备的时代风貌进行探讨。认为青年编辑要有“三心”“二意”,即坚定信心、胸怀匠心、不忘初心,牢固树立法治意识和市场意识。  相似文献   

17.
This article is a report of a concurrent session presented by Katherine Hill and Maria Collins of North Carolina State University (NCSU) Libraries at the 2013 North American Serials Interest Group conference. NCSU Libraries is a participant in the Global Open Knowledgebase (GOKb) project, which will provide an openly available knowledgebase for Kuali Open Library Environment (OLE). Results from a survey conducted by NCSU librarians are discussed, which focus on the e-resource management community and their expectations of the data provided in knowledgebases. The survey investigates problems and improvements in respect to data quality. Respondents also commented on their expectations of a community-managed project as well as the viability of a project like GOKb. Future directions and initiatives in the knowledgebase space were also summarized in the presentation.  相似文献   

18.
[目的/意义]通过对情感负荷理论的内涵、应用及相关研究发现的分析和总结,为国内同行进一步开展研究设计提供参考和借鉴。[方法/过程]通过文献调研与分析,追溯情感负荷理论提出的背景,对理论内涵进行阐述。并且,从理论形成之前、理论提出以及后续应用3个阶段对相关实证研究进行梳理,分析了该理论的形成发展过程,指出未来进一步研究方向。[结果/结论]情感负荷理论综合认知科学、情感神经科学、情感控制论和情感计算等多学科思想,从社会生物信息技术框架角度系统考察信息行为过程中的用户情感。情感负荷是一种消极的情绪,主要是刺激、焦虑、挫折、愤怒4种消极情绪随着时间压力而产生的一种不确定性。该理论被应用于虚拟图书馆、社交媒体等情境下对用户信息行为的研究。最后,指出未来研究方向。  相似文献   

19.
合作数字参考咨询服务模式探讨   总被引:18,自引:2,他引:18  
张喜年 《图书馆论坛》2006,26(3):275-278
文章提出合作数字参考咨询服务存在三种模式,并从成员管理、问题分配、知识库建设、服务支持等四个方面对三种模式的服务机制加以比较分析。  相似文献   

20.
ABSTRACT

Since its advent more than 15 years ago, the knowledgebase has quietly deposed the catalog as the center of the library management and discovery universe. Knowledgebases provide libraries with an inventory of their e-resources holdings and describe the materials that a library has purchased at a more granular level than the traditional bibliographic record. Knowledgebases power key tools such as link resolvers and unified search platforms, support management needs across the e-resources lifecycle, and more recently have evolved to intersect with areas such as linked open data, community contribution models, and next-generation library management platforms. They have truly become the hub from which our most vital services operate. This report will provide an overview of “The Knowledgebase at the Center of the Universe,” an American Library Association Technology Report assessing the state of knowledgebase technology. Topics covered will include an overview of the current product landscape, an exploration of new directions, and case studies from libraries and vendors using knowledgebases in innovative ways.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号