Search

We present the results of running 4 different papers through the automated filtering system used by the open access preprint server 'arXiv' to classify papers and implement quality control barriers. The exercise was carried out in order to assess whether these highly sophisticated, state-of-the-art filters can distinguish between papers that are controversial or have gone past their 'sell-by date,' and otherwise normal papers. We conclude that not even the arXiv filters, which are otherwise successful in filtering fringe-topic papers, can fully acquire 'Domain-Specific Discrimination' and thus distinguish technical papers that are taken seriously by an expert community from those that are not. Finally, we discuss the implications this has for citizen and policy-maker engagement with the Primary Source Knowledge of a technical domain. [ABSTRACT FROM AUTHOR]

Main path analysis is a popular method for extracting the scientific backbone from the citation network of a research domain. Existing approaches ignored the semantic relationships between the citing and cited publications, resulting in several adverse issues, in terms of coherence of main paths and coverage of significant studies. This paper advocated the semantic main path network analysis approach to alleviate these issues based on citation function analysis. A wide variety of SciBERT‐based deep learning models were designed for identifying citation functions. Semantic citation networks were built by either including important citations, for example, extension, motivation, usage and similarity, or excluding incidental citations like background and future work. Semantic main path network was built by merging the top‐K main paths extracted from various time slices of semantic citation network. In addition, a three‐way framework was proposed for the quantitative evaluation of main path analysis results. Both qualitative and quantitative analysis on three research areas of computational linguistics demonstrated that, compared to semantics‐agnostic counterparts, different types of semantic main path networks provide complementary views of scientific knowledge flows. Combining them together, we obtained a more precise and comprehensive picture of domain evolution and uncover more coherent development pathways between scientific ideas. [ABSTRACT FROM AUTHOR]

Combining computational technologies and humanities is an ongoing effort aimed at making resources such as texts, images, audio, video, and other artifacts digitally available, searchable, and analyzable. In recent years, deep neural networks (DNN) dominate the field of automatic text analysis and natural language processing (NLP), in some cases presenting a super‐human performance. DNNs are the state‐of‐the‐art machine learning algorithms solving many NLP tasks that are relevant for Digital Humanities (DH) research, such as spell checking, language detection, entity extraction, author detection, question answering, and other tasks. These supervised algorithms learn patterns from a large number of "right" and "wrong" examples and apply them to new examples. However, using DNNs for analyzing the text resources in DH research presents two main challenges: (un)availability of training data and a need for domain adaptation. This paper explores these challenges by analyzing multiple use‐cases of DH studies in recent literature and their possible solutions and lays out a practical decision model for DH experts for when and how to choose the appropriate deep learning approaches for their research. Moreover, in this paper, we aim to raise awareness of the benefits of utilizing deep learning models in the DH community. [ABSTRACT FROM AUTHOR]

With the growing use of artificial intelligence, search engine providers are increasingly pushing advertisers to use automated bidding strategies based on machine learning. Such automated decision‐making systems leave advertisers in the dark about the data being used and how they can influence the outcome of the decision‐making process. Previous literature on artificial intelligence lacks an understanding of the dangers related to artificially intelligent systems and their lack of transparency. In response, our paper addresses the inherent risks of the automated optimization of advertisers' bidding strategies in search engine advertising. The selected empirical case of a service company therefore demonstrates how data availability can trigger a long‐term decline in advertising performance and how search engine advertising performance metrics develop before and after an event of data scarcity. Based on data collected for 525 days, difference‐in‐differences analysis shows that the algorithmic approach has a considerable and lasting negative impact on advertising performance. Furthermore, the empirical case indicates that self‐regulated learning can initialize a downward spiral that gradually impairs advertising performance. Thus, the aim of this study is to increase awareness regarding automated decision‐making dangers in search engine advertising and help advertisers take preventive measures to reduce the risks of algorithm missteps. [ABSTRACT FROM AUTHOR]

As artificial intelligence (AI) technologies become more ubiquitous for streamlining and optimizing work, they are entering fields representing organizational logics at odds with the efficiency logic of automation. One such field is journalism, an industry defined by a logic enacted through professional norms, practices, and values. This paper examines the experience of technologists developing and employing natural language generation (NLG) in news organizations, looking at how they situate themselves and their technology in relation to newswork. Drawing on institutional logics, a theoretical framework from organizational theory, we show how technologists shape their logic for building these emerging technologies based on a theory of rationalizing news organizations, a frame of optimizing newswork, and a narrative of news organizations misinterpreting the technology. Our interviews reveal technologists mitigating tensions with journalistic logic and newswork by labeling stories generated by their systems as nonjournalistic content, seeing their technology as a solution for improving journalism, enabling newswork to move away from routine tasks. We also find that as technologists interact with news organizations, they assimilate elements from journalistic logic beneficial for benchmarking their technology for more lucrative industries. [ABSTRACT FROM AUTHOR]

Vast amounts of information are daily exchanged and/or released. The sensitive nature of much of this information creates a serious privacy threat when documents are uncontrollably made available to untrusted third parties. In such cases, appropriate data protection measures should be undertaken by the responsible organization, especially under the umbrella of current legislation on data privacy. To do so, human experts are usually requested to redact or sanitize document contents. To relieve this burdensome task, this paper presents a privacy model for document redaction/sanitization, which offers several advantages over other models available in the literature. Based on the well-established foundations of data semantics and information theory, our model provides a framework to develop and implement automated and inherently semantic redaction/ sanitization tools. Moreover, contrary to ad-hoc redaction methods, our proposal provides a priori privacy guarantees which can be intuitively defined according to current legislations on data privacy. Empirical tests performed within the context of several use cases illustrate the applicability of our model and its ability to mimic the reasoning of human sanitizers. [ABSTRACT FROM AUTHOR]

Conventional rule‐based approaches use exact template matching to capture linguistic information and necessarily need to enumerate all variations. We propose a novel flexible template generation and matching scheme called the principle‐based approach (PBA) based on sequence alignment, and employ it for reference metadata extraction (RME) to demonstrate its effectiveness. The main contributions of this research are threefold. First, we propose an automatic template generation that can capture prominent patterns using the dominating set algorithm. Second, we devise an alignment‐based template‐matching technique that uses a logistic regression model, which makes it more general and flexible than pure rule‐based approaches. Last, we apply PBA to RME on extensive cross‐domain corpora and demonstrate its robustness and generality. Experiments reveal that the same set of templates produced by the PBA framework not only deliver consistent performance on various unseen domains, but also surpass hand‐crafted knowledge (templates). We use four independent journal style test sets and one conference style test set in the experiments. When compared to renowned machine learning methods, such as conditional random fields (CRF), as well as recent deep learning methods (i.e., bi‐directional long short‐term memory with a CRF layer, Bi‐LSTM‐CRF), PBA has the best performance for all datasets. [ABSTRACT FROM AUTHOR]

Automated text categorization methods are of broad relevance for domain experts since they free researchers and practitioners from manual labeling, save their resources (e.g., time, labor), and enrich the data with information helpful to study substantive questions. Despite a variety of newly developed categorization methods that require substantial amounts of annotated data, little is known about how to build models when (a) labeling texts with categories requires substantial domain expertise and/or in‐depth reading, (b) only a few annotated documents are available for model training, and (c) no relevant computational resources, such as pretrained models, are available. In a collaboration with environmental scientists who study the socio‐ecological impact of funded biodiversity conservation projects, we develop a method that integrates deep domain expertise with computational models to automatically categorize project reports based on a small sample of 93 annotated documents. Our results suggest that domain expertise can improve automated categorization and that the magnitude of these improvements is influenced by the experts' understanding of categories and their confidence in their annotation, as well as data sparsity and additional category characteristics such as the portion of exclusive keywords that can identify a category. [ABSTRACT FROM AUTHOR]

Systematic reviews are essential for evaluating biomedical treatment options, but the growing size and complexity of the available biomedical literature combined with the rigor of the systematic review method mean that systematic reviews are extremely difficult and labor-intensive to perform. In this article, I propose a method of searching the literature by systematically mining the various types of citation relationships between articles. I then test the method by comparing its precision and recall to that of 14 published systematic reviews. The method successfully retrieved 74% of the studies included in these reviews and 90% of the studies it could reasonably be expected to retrieve. The method also retrieved fewer than half of the total number of publications retrieved by these reviews and can be performed in substantially less time. This suggests that the proposed method offers a promising complement to traditional text-based methods of literature identification and retrieval for systematic reviews. [ABSTRACT FROM AUTHOR]

This brief communication presents preliminary findings on automated Twitter accounts distributing links to scientific articles deposited on the preprint repository arXiv. It discusses the implication of the presence of such bots from the perspective of social media metrics (altmetrics), where mentions of scholarly documents on Twitter have been suggested as a means of measuring impact that is both broader and timelier than citations. Our results show that automated Twitter accounts create a considerable amount of tweets to scientific articles and that they behave differently than common social bots, which has critical implications for the use of raw tweet counts in research evaluation and assessment. We discuss some definitions of Twitter cyborgs and bots in scholarly communication and propose distinguishing between different levels of engagement-- that is, differentiating between tweeting only bibliographic information to discussing or commenting on the content of a scientific work. [ABSTRACT FROM AUTHOR]

This article presents a rare insight into the migration of municipality record‐keeping databases. The migration of a database for preservation purposes poses several challenges. In particular, our findings show that relevant issues are file‐format heterogeneity, collection volume, time and database structure evolution, and deviation from the governing standard. This article presents and discusses how such issues interfere with an organization's ability to undertake a migration, for preservation purposes, of records from a relational database. The case study at hand concerns six Norwegian municipality record‐keeping databases covering a period from 1999 to 2012. The findings are presented with a discussion on how these issues manifest themselves as a problem for long‐term preservation. The results discussed here may help an organization and Information Systems (IS) manager to establish a best practice when undertaking a migration project and enable them to avoid some of the pitfalls that were discovered during this project. [ABSTRACT FROM AUTHOR]

Records management in the public sector is integral for delivering public good. However, several institutional challenges inhibit the required implementation of innovative and information‐centric tools to transform records management in response to the challenges of digitization and to capitalize on new opportunities in the digital economy. In this article, we make recommendations to overcome institutional and legislative barriers to transform records management in the public sector. [ABSTRACT FROM AUTHOR]

The use of intelligent machines—digital technologies that feature data‐driven forms of customization, learning, and autonomous action—is rapidly growing and will continue to impact many industries and domains. This is consequential for communities of researchers, educators, and practitioners concerned with studying, supporting, and educating information professionals. In the face of new developments in artificial intelligence (AI), the research community faces 3 questions: (a) How is AI becoming part of the world of work? (b) How is the world of work becoming part of AI? and (c) How can the information community help address this topic of Work in the Age of Intelligent Machines (WAIM)? This opinion piece considers these 3 questions by drawing on discussion from an engaging 2019 iConference workshop organized by the NSF supported WAIM research coordination network (note: https://waim.network). [ABSTRACT FROM AUTHOR]

For laypeople, searching online health information resources can be challenging due to topic complexity and the large number of online sources with differing quality. The goal of this article is to examine, among all the available online sources, which online sources laypeople select to address their health‐related information needs, and whether or how much the severity of a health condition influences their selection. Twenty‐four participants were recruited individually, and each was asked (using a retrieval system called HIS) to search for information regarding a severe health condition and a mild health condition, respectively. The selected online health information sources were automatically captured by the HIS system and classified at both the website and webpage levels. Participants' selection behavior patterns were then plotted across the whole information‐seeking process. Our results demonstrate that laypeople's source selection fluctuates during the health information‐seeking process, and also varies by the severity of health conditions. This study reveals laypeople's real usage of different types of online health information sources, and engenders implications to the design of search engines, as well as the development of health literacy programs. [ABSTRACT FROM AUTHOR]

Currently, web document repositories have been collaboratively created and edited. One of these repositories, Wikipedia, is facing an important problem: assessing the quality of Wikipedia. Existing approaches exploit techniques such as statistical models or machine leaning algorithms to assess Wikipedia article quality. However, existing models do not provide satisfactory results. Furthermore, these models fail to adopt a comprehensive feature framework. In this article, we conduct an extensive survey of previous studies and summarize a comprehensive feature framework, including text statistics, writing style, readability, article structure, network, and editing history. Selected state‐of‐the‐art deep‐learning models, including the convolutional neural network (CNN), deep neural network (DNN), long short‐term memory (LSTMs) network, CNN‐LSTMs, bidirectional LSTMs, and stacked LSTMs, are applied to assess the quality of Wikipedia. A detailed comparison of deep‐learning models is conducted with regard to different aspects: classification performance and training performance. We include an importance analysis of different features and feature sets to determine which features or feature sets are most effective in distinguishing Wikipedia article quality. This extensive experiment validates the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

Authorship analysis attempts to reveal information about authors of digital documents enabling applications in digital humanities, text forensics, and cyber‐security. Author verification is a fundamental task where, given a set of texts written by a certain author, we should decide whether another text is also by that author. In this article we systematically study the usefulness of topic modeling in author verification. We examine several author verification methods that cover the main paradigms, namely, intrinsic (attempt to solve a one‐class classification task) and extrinsic (attempt to solve a binary classification task) methods as well as profile‐based (all documents of known authorship are treated cumulatively) and instance‐based (each document of known authorship is treated separately) approaches combined with well‐known topic modeling methods such as Latent Semantic Indexing (LSI) and Latent Dirichlet Allocation (LDA). We use benchmark data sets and demonstrate that LDA is better combined with extrinsic methods, while the most effective intrinsic method is based on LSI. Moreover, topic modeling seems to be particularly effective for profile‐based approaches and the performance is enhanced when latent topics are extracted by an enriched set of documents. The comparison to state‐of‐the‐art methods demonstrates the great potential of the approaches presented in this study. It is also demonstrates that even when genre‐agnostic external documents are used, the proposed extrinsic models are very competitive. [ABSTRACT FROM AUTHOR]

A correction to the article "Toward effective automated weighted subject indexing: A comparison of different approaches in different environments," published online is presented.

Subject indexing plays an important role in supporting subject access to information resources. Current subject indexing systems do not make adequate distinctions on the importance of assigned subject descriptors. Assigning numeric weights to subject descriptors to distinguish their importance to the documents can strengthen the role of subject metadata. Automated methods are more cost-effective. This study compares different automated weighting methods in different environments. Two evaluation methods were used to assess the performance. Experiments on three datasets in the biomedical domain suggest the performance of different weighting methods depends on whether it is an abstract or full text environment. Mutual information with bag-of-words representation shows the best average performance in the full text environment, while cosine with bag-of-words representation is the best in an abstract environment. The cosine measure has relatively consistent and robust performance. A direct weighting method, IDF (Inverse Document Frequency), can produce quick and reasonable estimates of the weights. Bag-of-words representation generally outperforms the concept-based representation. Further improvement in performance can be obtained by using the learning-to-rank method to integrate different weighting methods. This study follows up Lu and Mao (Journal of the Association for Information Science and Technology, 66, 1776-1784, 2015), in which an automated weighted subject indexing method was proposed and validated. The findings from this study contribute to more effective weighted subject indexing. [ABSTRACT FROM AUTHOR]

This article explores the effects of health information technologies (HIT) in operating rooms (ORs). When functioning well, HIT are a boon to mankind. However, HIT in the OR also create hazards for patients for a number of interrelated reasons. We introduce 5 interrelated components of hazard situations for medical teams operating in the OR: complexity, overload/underload, inadequate individual training, inadequate training of medical teams, and overconfidence of surgeons. These components of hazard situations in the OR may negatively impact patient safety. We discuss implications, especially in terms of individuals and medical teams in the OR, as well as work substitution as a broader aspect of the potential dark side of health IT. [ABSTRACT FROM AUTHOR]

Tools for automatic subject assignment help deal with scale and sustainability in creating and enriching metadata, establishing more connections across and between resources and enhancing consistency. Although some software vendors and experimental researchers claim the tools can replace manual subject indexing, hard scientific evidence of their performance in operating information environments is scarce. A major reason for this is that research is usually conducted in laboratory conditions, excluding the complexities of real-life systems and situations. The article reviews and discusses issues with existing evaluation approaches such as problems of aboutness and relevance assessments, implying the need to use more than a single "gold standard" method when evaluating indexing and retrieval, and proposes a comprehensive evaluation framework. The framework is informed by a systematic review of the literature on evaluation approaches: evaluating indexing quality directly through assessment by an evaluator or through comparison with a gold standard, evaluating the quality of computer-assisted indexing directly in the context of an indexing workflow, and evaluating indexing quality indirectly through analyzing retrieval performance. [ABSTRACT FROM AUTHOR]