基于支持向量机的文本自动分类试验研究

提出了将支持向量机应用于文本自动分类的研究，与常用的K-最邻近法相比，无论是对训练数据集还是测试数据集均具有一定的优势，而且不同特征选择方法对支持向量机的影响要比K-最邻近法小。此外，从研究中的不同特征选择的评价函数来看，它们对分类有一定的影响，应用X2统计进行特征选择的分类正确率最高，其次是文本证据权，而期望交叉熵的效果最差，说明特征选择在文本自动分类中也是相当重要的。     

新闻形态论

新闻形态是指新闻的存在方式与状态。新闻的存在 ,无论是从新闻传播现象的历史过程看 ,还是从一次新闻传播的历时过程看 ,都有形态的演变。新闻形态论的提出 ,对从学术上厘清“新闻”概念的具体含义 ,实践上把握新闻传播的内在运作机制 ,都具有重要的启发意义     

利用TRS全文检索系统建设动态图书馆网站

本介绍了选择TRS全检索系统建设动态图书馆网站的背景；TRS系统的体系结构，各部分的功能；详细探讨了TRS系统在图书馆网站中的应用，结合建设实践，探讨了在应用中的一些实际问题的解决。     

Nurturing Authority

When considering the role of local journalism in a networked media environment, it is crucial to examine how audiences attribute news with the power to define social knowledge. In particular, television news programs need to appeal to audiences by reinforcing a sense of local journalistic authority to assert the parameters of who and what is worthy of coverage. This article presents the findings from interviews with a range of commercial television news viewers in Sydney, Australia. It positions viewership in the context of people’s wider engagement with news, and in relation to their interpersonal and digital social interactions. The paper argues that local audiences have conflicting attitudes to the role of television news, both contesting and re-inscribing the programs with the power to demarcate social, political, and cultural knowledge. It traces how local audiences challenge the ability of news to convey boundaries within the community through processes of exclusion, connecting the contestations to the lived experiences of the individuals. It identifies that television news programs nurture journalistic authority in terms of their local relevance, and it contributes insights on the significance of local news by engaging with the means by which audiences themselves attach social power to journalism.     

A Follower-Centric Approach to Leadership in the Newsroom

This article analyses leadership in the newsroom of the Spanish newspaper El País as well as its impact on the craft of journalism more generally. Through 23 in-depth interviews, we try to elucidate how the newsroom constructs its leaders (in the newsroom, what does it mean to be a leader?), paying particular attention to the main skills considered to be necessary. According to our newsroom findings, not all heads of section or editors-in-chief are leaders, a fact that questions formal authority relations and proclaims expertise and know-how as discriminatory skills. This study emphasizes that the collective recognition of a leader is not an ultimate disposition, but can vary over time: consequently leaders who do not achieve the professional requirements of the newsroom can be denied the status, despite their expertise and experience. Our findings indicate that leaders at El País are those journalists (no matter what their positions) with strong capacities and skills (fundamentally experience, expertise and creativity) to manage form (relationships) and substance (contents) in the daily work of the newsroom. In short, journalists seen as leaders combine reiterated and strong qualities and merit, graphically reflected in the texts they have published for years in the newspaper.     

Citizen-Centered Journalism and Contested Boundaries

This article explores the existence of a “citizen-centered journalism” that sees citizens as crucial participants in the construction of news and as co-creators of their own worlds. Through qualitative case studies of three news organizations, the article examines the motivation for using a citizen-centered approach, the news routines that are required to do so, the categories of content produced, and the perceived impact of this approach. The results suggest these news organizations are working in partnership with communities and striving to give a voice to historically marginalized communities. The journalists, however, see citizen participation as complementary to professional journalistic routines that favor verifiable information, rather than assigning inherent value to it for its own sake.     

Placing Facebook

Facebook is challenging professional journalism. These challenges were evident in three incidents from 2016: the allegation that Facebook privileged progressive-leaning news on its trending feature; Facebook’s removal of the Pulitzer Prize-winning “Napalm Girl” photo from the pages of prominent users; and the proliferation of “fake news” during the US presidential election. Using theoretical concepts from the field of boundary work, this paper examines how The Guardian, The New York Times, Columbia Journalism Review and Poynter editorialized Facebook’s role in these three incidents to discursively construct the boundary between the value of professional journalism to democracy and Facebook’s ascendant role in facilitating essential democratic functions. Findings reveal that these publications attempted to define Facebook as a news organization (i.e., include it within the boundaries of journalism) so that they could then criticize the company for not following duties traditionally incumbent upon news organizations (i.e., place it outside the boundaries of journalism). This paper advances scholarship that focuses on both inward and outward conceptions of boundary work, further explores the complex challenge of defining who a journalist is in the face of rapidly changing technological norms, and advances scholarship in the field of media ethics that positions ethical analysis at the institutional level.     

基于论文与专利整合数据的研究方向发现模型研究

海量信息分析及基于分析结果得出相应的结论是一项非常重要的工作,该工作需要投入大量的时间和精力。本文涉及了基于论文与专利整合数据的研究方向发现模型,从论文和专利共同研究方向和新兴技术两个方面来揭示论文和专利之间关系,最后,我们对电动汽车论文和专利数据进行了实例验证。     

种子概念方法及其在基于文本的本体学习中的应用

介绍基于文本的本体学习及其层次,分析本体学习中术语获取的主要方法。针对术语获取中存在的问题,在术语形成的经济规律基础上,引入种子概念方法,并利用统计和规则两种方法抽取与种子概念相关的领域术语;证明种子概念方法是一种有效获取领域术语的方法。实验证明少量种子词可以获取大量领域术语,为本体构建提供基础和框架。     

NFCNNC:一种新的模糊竞争神经网络聚类模型及其在文本聚类中的应用

提出了一种新的模糊竞争神经网络聚类模型NFCNNC,并将其应用到文本聚类中。NFCNNC将模糊中心聚类(FCC)算法得到的模糊聚类中心向量作为神经网络的权值,通过比较隶属度值得到获胜神经元。网络中仅两个神经元同时调节权值。隶属度值最大的神经元以较大的学习率调整权值,隶属度次大的神经元以较小的学习率调整权值,其他神经元权值不变。按照FCC算法调整模糊聚类中心向量值(即权值)和神经元的隶属度,当网络稳定时,即可确定聚类数。与传统模糊神经网络模型相比,本文的模糊神经网络模型具有结构简单、运行效率高、聚类精度高的优点,同时克服了传统算法需预先指定聚类数的局限性。通过对文本聚类的实验验证,本算法取得了良好的效果。