基于Doc2vec和SVM的作者姓名消歧研究 ——以PubMed Central为例

【目的/意义】为解决重名作者姓名识别问题,提升作者姓名消歧准确率。【方法/过程】本文着重在整合作 者单位、邮箱等信息特征的基础上抓住作者在研究方向和研究内容上的承接性和演进性,提出构建综合文章题目、 关键词、摘要、引文以及作者的合作列表、邮箱、机构等附属信息的作者语料集,利用Doc2ve进行深度本文表示学 习,在特征学习的基础上利用支持向量机（SVM）根据人工标注的样本进行模型训练和学习,以 PubMed Central （PMC）全部数据为例,在得到局部较优结果的基础上,将模型用于PMC所有数据集。【结果/结论】结果显示本文提 出的姓名消歧方法准确率达91.80%,有效提升了消歧的准确率,该方法不仅把握了传统作者机构、邮箱、合作列表 等特征信息,而且根据作者研究内容的承接性和演进性追溯作者,整合多方面特征以解决单单依据单位、邮箱等信 息消歧失效问题,面对学者流动性的增强展示出其更强的应用前景。【创新/局限】本研究将每个作者分别包装成一 个个文档,以此包含作者的所有属性以及相关信息,通过无监督文本表示学习和有监督机器学习结合的模式完成 消歧任务,在生命科学与医学领域数据方面具有较好的适用性。     

Multi-Aspect Review-Team Assignment using Latent Research Areas

Reviewer assignment is an important task in many research-related activities, such as conference organization and grant-proposal adjudication. The goal is to assign each submitted artifact to a set of reviewers who can thoroughly evaluate all aspects of the artifact’s content, while, at the same time, balancing the workload of the reviewers. In this paper, we focus on textual artifacts such as conference papers, where both (aspects of) the submitted papers and (expertise areas of) the reviewers can be described with terms and/or topics extracted from the text. We propose a method for automatically assigning a team of reviewers to each submitted paper, based on the clusters of the reviewers’ publications as latent research areas. Our method extends the definition of the relevance score between reviewers and papers using the latent research areas information to find a team of reviewers for each paper, such that each individual reviewer and the team as a whole cover as many paper aspects as possible. To solve the constrained problem where each reviewer has a limited reviewing capacity, we utilize a greedy algorithm that starts with a group of reviewers for each paper and iteratively evolves it to improve the coverage of the papers’ topics by the reviewers’ expertise. We experimentally demonstrate that our method outperforms state-of-the-art approaches w.r.t several standard quality measures.     

Amplifying scientific paper’s abstract by leveraging data-weighted reconstruction

In this paper, we focus on the problem of automatically generating amplified scientific paper’s abstract which represents the most influential aspects of scientific paper. The influential aspects can be illustrated by the target scientific paper’s abstract and citation sentences discussing the target paper, which are provided in papers citing the target paper. In this paper, we extract representative sentences through data-weighted reconstruction approach(DWR) by jointly leveraging target scientific paper’s abstract and citation sentences’ content and structure. In our study, we make two-folded contributions.Firstly, sentence’s weight was learned by exploiting regularization for ranking on heterogeneous bibliographic network. Specially, Sentences-similar-Sentences relationship was identified by language modeling-based approach and added to the bibliographic network. Secondly, a data-weighted reconstruction objective function is optimized to select the most representative sentences which reconstructs the original sentence set with minimum error. In this process, sentences’ weight plays a critical role. Experimental evaluation over real dataset confirms the effectiveness of our approach.     

内容信息与引文信息融合的作者影响力评价研究

[目的/意义]为弥补现有作者影响力评价指标缺乏内容信息的不足,发现不同研究主题下高影响力的作者,文章给出一种基于主题内容的作者影响力评价方法。[方法/过程]以情报学领域近5年核心期刊的文献为样本,首先利用CTM模型提取样本文献的主题,获得文献作者对不同主题的贡献值;再利用K-means算法对样本文献分类,由此将文献对应的作者划分到特定主题类别下;然后,将作者在某特定主题类别的贡献值与作者发表文献的平均被引频次相结合,设计特定主题类别下作者影响力指标(Author Influence Index in Specific Topic,AII-ST);最后,根据AII-ST值对作者进行影响力排序。[结果/结论]本研究在方法上,通过CTM模型与K-means算法的结合实现了K-means算法初始聚类中心与聚类数目的双重优化;在应用中,作者评价指标AII-ST值能有效限定作者的比较范围,较好地反映作者的研究方向;新指标评价视角新颖、评价结果可靠。     

Implicit information need as explicit problems,help, and behavioral signals

Information need is one of the most fundamental aspects of information seeking, which traditionally conceptualizes as the initiation phase of an individual’s information seeking behavior. However, the very elusive and inexpressible nature of information need makes it hard to elicit from the information seeker or to extract through an automated process. One approach to understanding how a person realizes and expresses information need is to observe their seeking behaviors, to engage processes with information retrieval systems, and to focus on situated performative actions. Using Dervin’s Sense-Making theory and conceptualization of information need based on existing studies, the work reported here tries to understand and explore the concept of information need from a fresh methodological perspective by examining users’ perceived barriers and desired helps in different stages of information search episodes through the analyses of various implicit and explicit user search behaviors. In a controlled lab study, each participant performed three simulated online information search tasks. Participants’ implicit behaviors were collected through search logs, and explicit feedback was elicited through pre-task and post-task questionnaires. A total of 208 query segments were logged, along with users’ annotations on perceived problems and help. Data collected from the study was analyzed by applying both quantitative and qualitative methods. The findings identified several behaviors – such as the number of bookmarks, query length, number of the unique queries, time spent on search results observed in the previous segment, the current segment, and throughout the session – strongly associated with participants’ perceived barriers and help needed. The findings also showed that it is possible to build accurate predictive models to infer perceived problems of articulation of queries, useless and irrelevant information, and unavailability of information from users’ previous segment, current segment, and whole session behaviors. The findings also demonstrated that by combining perceived problem(s) and search behavioral features, it was possible to infer users’ needed help(s) in search with a certain level of accuracy (78%).     

智能化企业电子邮件分类管理模型研究

通过对电子邮件数据具有的特点和电子邮件数据表示的介绍,从数据管理、技术、应用等三个方面对电子邮件管理的内涵进行了分析。在分析的基础上提出了数据-技术-应用(DTA)电子邮件管理框架,进一步得出了以邮件知识管理为核心的智能化企业电子邮件管理系统模型。     

An enterprise resource planning system innovation and its influence on organisational culture: a case study in higher education

Many organisations are adopting new enterprise resource planning (ERP) systems to address their organisational and business problems. These technologies may promise utopian visions of information management, yet often they have the potential to re-shape organisational life and bring even more control to the workplace; in some instances outcomes that are unpredictable and detrimental to the organisation. The study of ERPs and their influence on organisational life and culture is a complex and highly contested area of research which has been the subject of much theorising. This paper adds to the debate through a longitudinal case study of an integrated information system implementation undertaken within a large UK university. The system (known as SITS – strategic information technology services) was introduced into a university in 2006 and the focus of the research has been on culture change within the SITS environment. Document analysis, interviews and participant observation were used to collect data. What has emerged from this study is that many current approaches are unable to account for the complexity of cultural studies within an integrated information systems environment. Therefore we have adopted an approach which acknowledges technology’s power to facilitate or constrain, as well as the role that individuals play in the use of technology to organise.     

Analysis of multiple query reformulations on the web: The interactive information retrieval context

This study examines the facets and patterns of multiple Web query reformulations with a focus on reformulation sequences. Based on IR interaction models, it was presumed that query reformulation is the product of the interaction between the user and the IR system. Query reformulation also reflects the interplay between the surface and deeper levels of user interaction. Query logs were collected from a Web search engine through the selection of search sessions in which users submitted six or more unique queries per session. The final data set was composed of 313 search sessions. Three facets of query reformulation (content, format, and resource) as well as nine sub-facets were derived from the data. In addition, analysis of modification sequences identified eight distinct patterns: specified, generalized, parallel, building-block, dynamic, multitasking, recurrent, and format reformulation. Adapting Saracevic’s stratified model, the authors develop a model of Web query reformulation based on the results of the study. The implications for Web search engine design are finally discussed and the functions of an interactive reformulation tool are suggested.     

Measuring the impact of spammers on e-mail and Twitter networks

This paper investigates the research question if senders of large amounts of irrelevant or unsolicited information – commonly called “spammers” – distort the network structure of social networks. Two large social networks are analyzed, the first extracted from the Twitter discourse about a big telecommunication company, and the second obtained from three years of email communication of 200 managers working for a large multinational company. This work compares network robustness and the stability of centrality and interaction metrics, as well as the use of language, after removing spammers and the most and least connected nodes. The results show that spammers do not significantly alter the structure of the information-carrying network, for most of the social indicators. The authors additionally investigate the correlation between e-mail subject line and content by tracking language sentiment, emotionality, and complexity, addressing the cases where collecting email bodies is not permitted for privacy reasons. The findings extend the research about robustness and stability of social networks metrics, after the application of graph simplification strategies. The results have practical implication for network analysts and for those company managers who rely on network analytics (applied to company emails and social media data) to support their decision-making processes.     

Exploring payment behavior for live courses in social Q&A communities: An information foraging perspective

People are increasingly searching for information in social Q&A communities, especially through a new form of paid knowledge product, namely, live course. Such course provides a way for users to interact synchronously with content creators online. However, how this knowledge product is accepted and why users pay for it deserve attention from researchers. In this study, a research model was developed based on information foraging theory (IFT) and social information foraging (SIF) theory to analyze users’ information processing and evaluation when making payment decisions. Our research model was validated by collecting subjective and objective data from a Chinese social Q&A community that has been successful in offering live course services. We found that perceived quality of free content, perceived credibility of content creators, and perceived quantity of participants positively influence users’ willingness to pay, and thus, positively affects users’ payment behavior. Unexpectedly, social endorsement negatively moderates the relationship between willingness to pay and payment behavior. This study enhances the theoretical understanding of the drivers of users’ payment for live courses in social Q&A communities. For IS practice, our findings provide unique insights for community managers and content creators on how to operate paid knowledge products appropriately and effectively.     

为了科学,还是为了公众?——论公众科学的两种进路

自20世纪90年代中期以来,“公众科学”的概念逐渐受到学界关注并形成了一个新的研究领域,但目前学界对于“公众科学”的内涵仍没有共识。为此本文追溯了实践进路和政治进路两种不同内涵的公众科学的源起、内容与影响,并对两种公众科学的形成背景、理论预设、政策影响等方面的差异进行了系统比较;同时阐述了已有研究对于融合两种公众科学进路的尝试。最后,文章提出公众科学是一种以公众为主体的新知识生产方式,并结合国内公众科学情况提出了几点发展建议。     

An empirical investigation of information sharing behavior on social commerce sites

Social commerce sites (SCSs), a new model of social media, provide fertile ground for customers to communicate their opinions and exchange product- or service- related information. Given the significant opportunities related to the use of social media data for customers’ insight, we explore the factors driving information sharing behavior on SCSs. In this paper, we propose and empirically test a comprehensive theoretical model for customer information sharing behavior through analysis of online survey data as well as network and behavioral usage data of over four months from 1177 customers in a SCS. The research model was empirically validated with the use of both subjective and objective data in a longitudinal setting. Our results show that customer information sharing is influenced by both individual (i.e., reputation and the enjoyment of helping others) and social capital (i.e., out-degrees’ post, in-degrees’ feedback, customer expertise and reciprocity) factors. This study contributes to the existing literature by highlighting the role of directed social network in customer information sharing behavior on SCSs. We believe that the results of our study offer important insights to the IS research and practice.     

Semantic search for public opinions on urban affairs: A probabilistic topic modeling-based approach

The explosion of online user-generated content (UGC) and the development of big data analysis provide a new opportunity and challenge to understand and respond to public opinions in the G2C e-government context. To better understand semantic searching of public comments on an online platform for citizens’ opinions about urban affairs issues, this paper proposed an approach based on the latent Dirichlet allocation (LDA), a probabilistic topic modeling method, and designed a practical system to provide users—municipal administrators of B-city—with satisfying searching results and the longitudinal changing curves of related topics. The system is developed to respond to actual demand from B-city's local government, and the user evaluation experiment results show that a system based on the LDA method could provide information that is more helpful to relevant staff members. Municipal administrators could better understand citizens’ online comments based on the proposed semantic search approach and could improve their decision-making process by considering public opinions.     

基于双重进入许可的电子政务个性化信息服务研究

文章以电子邮件为对象,基于双重进入许可方式,构建了一个电子政务个性化信息服务模型。在此基础之上,本文深入分析了电子政务个性化信息服务中的用户建模和个性化推荐,并对电子政务个性化信息服务的两个关键问题：公众信息分类和邮件阅读率追踪与获取进行了进一步研究。     

Online community information seeking: The queries of three communities in Southwestern Ontario

This paper presents not only mycommunityinfo.ca (MCI) as an innovative World Wide Web (WWW)-based community information (CI) site, but also how its unique approach to facilitating online CI searching on the Web reveals through empirical data how people use such information and communication technologies (ICTs) to address their everyday information needs. The geographic focus for this study is on three communities in Southwestern Ontario. MCI collects unobtrusively query data that are logged daily from its own Web site, the Web sites of three municipal governments, and one municipal agency from this region. One year’s worth of these data was supplied to determine the types of CI that are sought through Web searching. A content analysis of a large purposive sample of all of MCI’s query data reveals more specific and diverse conceptual CI needs between and within communities than those reported in other studies employing different data collection methods. As a result, using a centralized approach to online CI access via the WWW by other CI providers such as the 211 network may be a disservice to its users. Additionally, the findings demonstrate how a thorough analysis of such data may improve the informational content and overall design of municipal government Web sites. The analysis of these data also has the potential of improving current CI taxonomies.     

Through the kaleidoscope: Perspectives on cultural change within an integrated information systems environment

The study of information systems and their influence on organisational culture is a complex and highly contested area of research which has been the subject of much theorising. This paper intends to add to the debate through a longitudinal case study of an integrated information system implementation undertaken within a large UK university. The system known as SITS (Strategic Information Technology Services) was introduced into the university in 2006 and the focus of the research has been on culture change within the SITS environment. Document analysis, interviews and participant observation were used to collect the data for this study. What has emerged from this study is that current approaches are unable to account for the complexity of cultural studies within an integrated information systems environment and therefore we have developed the concept of the ‘cultural kaleidoscope’ as a heuristic to better understand the nature of cultural change within these circumstances.     

Ontology-based affective models to organize artworks in the social semantic web

In this paper, we focus on applying sentiment analysis to resources from online art collections, by exploiting, as information source, tags intended as textual traces that visitors leave to comment artworks on social platforms. We present a framework where methods and tools from a set of disciplines, ranging from Semantic and Social Web to Natural Language Processing, provide us the building blocks for creating a semantic social space to organize artworks according to an ontology of emotions. The ontology is inspired by the Plutchik’s circumplex model, a well-founded psychological model of human emotions. Users can be involved in the creation of the emotional space, through a graphical interactive interface. The development of such semantic space enables new ways of accessing and exploring art collections.The affective categorization model and the emotion detection output are encoded into W3C ontology languages. This gives us the twofold advantage to enable tractable reasoning on detected emotions and related artworks, and to foster the interoperability and integration of tools developed in the Semantic Web and Linked Data community. The proposal has been evaluated against a real-word case study, a dataset of tagged multimedia artworks from the ArsMeteo Italian online collection, and validated through a user study.     

Approach or avoid? The dualistic effects of envy on social media users’ behavioral intention

People express themselves through posts or selfies with brands and activities on social networking sites (SNSs) such as Facebook and Instagram. This user-generated content provides adequate social information that may elicit the emotions of users who are exposed to such content on these online platforms. Although academic researchers have focused on factors affecting users’ emotions on SNSs, how users reconcile both positive and negative emotions to their attitude and behavior in triadic interactions remains unclear. The current study attempted to answer this research question through the lens of social comparison theory by investigating the effects of tie strength and focus of attention as two forces eliciting online social comparisons on emotional consequences measured through pleasure and envy. Moreover, the dualistic effects of the two distinct types of envy, namely benign and malicious, and the effect of pleasure on users’ approach and avoidance behavior were explored and hypothesized. The results indicated that strong ties triggered more benign envy compared with malicious envy. Furthermore, benign envy positively affected brand attitude and SNS avoidance in terms of exhaustion, whereas malicious envy negatively influenced brand attitude and increased the likelihood of SNS avoidance in terms of both exhaustion and discontinuance.