Diese Datenbank enthält über 40.000 Dokumente zu Themen aus den Bereichen Formalerschließung – Inhaltserschließung – Information Retrieval.
© 2015 W. Gödert, TH Köln, Institut für Informationswissenschaft / Powered by litecat, BIS Oldenburg (Stand: 04. Juni 2021)
1Sun, J. ; Zhu, M. ; Jiang, Y. ; Liu, Y. ; Wu, L.L.: Hierarchical attention model for personalized tag recommendation : peer effects on information value perception.
In: Journal of the Association for Information Science and Technology. 72(2021) no.2, S.173-189.
Abstract: With the development of Web-based social networks, many personalized tag recommendation approaches based on multi-information have been proposed. Due to the differences in users' preferences, different users care about different kinds of information. In the meantime, different elements within each kind of information are differentially informative for user tagging behaviors. In this context, how to effectively integrate different elements and different information separately becomes a key part of tag recommendation. However, the existing methods ignore this key part. In order to address this problem, we propose a deep neural network for tag recommendation. Specifically, we model two important attentive aspects with a hierarchical attention model. For different user-item pairs, the bottom layered attention network models the influence of different elements on the features representation of the information while the top layered attention network models the attentive scores of different information. To verify the effectiveness of the proposed method, we conduct extensive experiments on two real-world data sets. The results show that using attention network and different kinds of information can significantly improve the performance of the recommendation model, and verify the effectiveness and superiority of our proposed model.
Inhalt: Vgl.: https://asistdl.onlinelibrary.wiley.com/doi/10.1002/asi.24400.
2Tang, X.-B. ; Fu, W.-G. ; Liu, Y.: Knowledge big graph fusing ontology with property graph : a case study of financial ownership network.
In: Knowledge organization. 48(2021) no.1, S.55-71.
Abstract: The scale of knowledge is growing rapidly in the big data environment, and traditional knowledge organization and services have faced the dilemma of semantic inaccuracy and untimeliness. From a knowledge fusion perspective-combining the precise semantic superiority of traditional ontology with the large-scale graph processing power and the predicate attribute expression ability of property graph-this paper presents an ontology and property graph fusion framework (OPGFF). The fusion process is divided into content layer fusion and constraint layer fusion. The result of the fusion, that is, the knowledge representation model is called knowledge big graph. In addition, this paper applies the knowledge big graph model to the ownership network in the China's financial field and builds a financial ownership knowledge big graph. Furthermore, this paper designs and implements six consistency inference algorithms for finding contradictory data and filling in missing data in the financial ownership knowledge big graph, five of which are completely domain agnostic. The correctness and validity of the algorithms have been experimentally verified with actual data. The fusion OPGFF framework and the implementation method of the knowledge big graph could provide technical reference for big data knowledge organization and services.
Anmerkung: Part of: Special issue: Domain ontologies, part 2.
3Wei, W. ; Liu, Y.-P. ; Wei, L-R.: Feature-level sentiment analysis based on rules and fine-grained domain ontology.
In: Knowledge organization. 47(2020) no.2, S.105-121.
Abstract: Mining product reviews and sentiment analysis are of great significance, whether for academic research purposes or optimizing business strategies. We propose a feature-level sentiment analysis framework based on rules parsing and fine-grained domain ontology for Chinese reviews. Fine-grained ontology is used to describe synonymous expressions of product features, which are reflected in word changes in online reviews. First, a semiautomatic construction method is developed by using Word2Vec for fine-grained ontology. Then, featurelevel sentiment analysis that combines rules parsing and the fine-grained domain ontology is conducted to extract explicit and implicit features from product reviews. Finally, the domain sentiment dictionary and context sentiment dictionary are established to identify sentiment polarities for the extracted feature-sentiment combinations. An experiment is conducted on the basis of product reviews crawled from Chinese e-commerce websites. The results demonstrate the effectiveness of our approach.
4Liu, Y. ; Du, F. ; Sun, J. ; Silva, T. ; Jiang, Y. ; Zhu, T.: Identifying social roles using heterogeneous features in online social networks.
In: Journal of the Association for Information Science and Technology. 70(2019) no.7, S.660-674.
Abstract: Role analysis plays an important role when exploring social media and knowledge-sharing platforms for designing marking strategies. However, current methods in role analysis have overlooked content generated by users (e.g., posts) in social media and hence focus more on user behavior analysis. The user-generated content is very important for characterizing users. In this paper, we propose a novel method which integrates both user behavior and posted content by users to identify roles in online social networks. The proposed method models a role as a joint distribution of Gaussian distribution and multinomial distribution, which represent user behavioral feature and content feature respectively. The proposed method can be used to determine the number of roles concerned automatically. The experimental results show that the proposed method can be used to identify various roles more effectively and to get more insights on such characteristics.
Inhalt: Vgl.: https://onlinelibrary.wiley.com/doi/10.1002/asi.24160.
5Wu, Y. ; Liu, Y. ; Tsai, Y.-H.R. ; Yau, S.-T.: Investigating the role of eye movements and physiological signals in search satisfaction prediction using geometric analysis.
In: Journal of the Association for Information Science and Technology. 70(2019) no.9, S.981-999.
Abstract: Two general challenges faced by data analysis are the existence of noise and the extraction of meaningful information from collected data. In this study, we used a multiscale framework to reduce the effects caused by noise and to extract explainable geometric properties to characterize finite metric spaces. We conducted lab experiments that integrated the use of eye-tracking, electrodermal activity (EDA), and user logs to explore users' information-seeking behaviors on search engine result pages (SERPs). Experimental results of 1,590 search queries showed that the proposed strategies effectively predicted query-level user satisfaction using EDA and eye-tracking data. The bootstrap analysis showed that combining EDA and eye-tracking data with user behavior data extracted from user logs led to a significantly better linear model fit than using user behavior data alone. Furthermore, cross-user and cross-task validations showed that our methods can be generalized to different search engine users performing different preassigned tasks.
Inhalt: Vgl.: https://onlinelibrary.wiley.com/doi/10.1002/asi.24240.
Anmerkung: Beitrag in einem 'Special issue on neuro-information science'.
6Qin, C. ; Liu, Y. ; Mou, J. ; Chen, J.: User adoption of a hybrid social tagging approach in an online knowledge community.
In: Aslib journal of information management. 71(2019) no.2, S.155-175.
Abstract: Purpose Online knowledge communities make great contributions to global knowledge sharing and innovation. Resource tagging approaches have been widely adopted in such communities to describe, annotate and organize knowledge resources mainly through users' participation. However, it is unclear what causes the adoption of a particular resource tagging approach. The purpose of this paper is to identify factors that drive users to use a hybrid social tagging approach. Design/methodology/approach Technology acceptance model and social cognitive theory are adopted to support an integrated model proposed in this paper. Zhihu, one of the most popular online knowledge communities in China, is taken as the survey context. A survey was conducted with a questionnaire and collected data were analyzed through structural equation model. Findings A new hybrid social resource tagging approach was refined and described. The empirical results revealed that self-efficacy, perceived usefulness (PU) and perceived ease of use exert positive effect on users' attitude. Moreover, social influence, PU and attitude impact significantly on users' intention to use a hybrid social resource tagging approach. Originality/value Theoretically, this study enriches the type of resource tagging approaches and recognizes factors influencing user adoption to use it. Regarding the practical parts, the results provide online information system providers and designers with referential strategies to improve the performance of the current tagging approaches and promote them.
Inhalt: Vgl.: https://doi.org/10.1108/AJIM-09-2018-0212.
Themenfeld: Social tagging
7Liu, Y. ; Shi, J. ; Chen, Y.: Patient-centered and experience-aware mining for effective adverse drug reaction discovery in online health forums.
In: Journal of the Association for Information Science and Technology. 69(2018) no.2, S.215-228.
Abstract: Adverse Drug Reactions (ADRs) have become a serious health problem and even a leading cause of death in the United States. Pre-marketing clinical trials and traditional post-marketing surveillance using voluntary and spontaneous report systems are insufficient for ADR detection. On the other hand, online health forums provide valuable evidences in a large scale and in a timely fashion through the active participation of patients, caregivers, and doctors. In this article, we present patient-centered and experience-aware mining framework for effective ADR discovery using online health forum data. Our experimental evaluation with both an official ADR knowledge base and human-annotated ground truth verifies the effectiveness of the proposed method for ADR discovery.
Inhalt: Vgl.: http://onlinelibrary.wiley.com/doi/10.1002/asi.23929/full.
8Zhou, H. ; Xiao, L. ; Liu, Y. ; Chen, X.: ¬The effect of prediscussion note-taking in hidden profile tasks.
In: Journal of the Association for Information Science and Technology. 69(2018) no.4, S.566-577.
Abstract: Prior research has discovered that groups tend to discuss shared information while failing to discuss unique information in decision-making processes. In our study, we conducted a lab experiment to examine the effect of prediscussion note-taking on this phenomenon. The experiment used a murder-mystery hidden profile task. In all, 192 undergraduate students were recruited and randomly assigned into 48 four-person groups with gender being the matching variable (i.e., each group consisted of four same-gender participants). During the decision-making processes, some groups were asked to take notes while reading task materials and had their notes available in the following group discussion, while the other groups were not given this opportunity. Our analysis results suggest that (a) the presence of an information piece in group members' notes positively correlates with its appearance in the subsequent discussion and note-taking positively affects the group's information repetition rate; (b) group decision quality positively correlates with the group's information sampling rate and negatively correlates with the group's information sampling/repetition bias; and (c) gender has no statistically significant moderating effect on the relationship between note-taking and information sharing. These results imply that prediscussion note-taking could facilitate information sharing but could not alleviate the biased information pooling in hidden profile tasks.
Inhalt: Vgl.: https://onlinelibrary.wiley.com/doi/abs/10.1002/asi.23976.
9Liu, Y. ; Xu, S. ; Blanchard, E.: ¬A local context-aware LDA model for topic modeling in a document network.
In: Journal of the Association for Information Science and Technology. 68(2017) no.6, S.1429-1448.
Abstract: With the rapid development of the Internet and its applications, growing volumes of documents increasingly become interconnected to form large-scale document networks. Accordingly, topic modeling in a network of documents has been attracting continuous research attention. Most of the existing network-based topic models assume that topics in a document are influenced by its directly linked neighbouring documents in a document network and overlook the potential influence from indirectly linked ones. The existing work also has not carefully modeled variations of such influence among neighboring documents. Recognizing these modeling limitations, this paper introduces a novel Local Context-Aware LDA Model (LC-LDA), which is capable of observing a local context comprising a rich collection of documents that may directly or indirectly influence the topic distributions of a target document. The proposed model can also differentiate the respective influence of each document in the local context on the target document according to both structural and temporal relationships between the two documents. The proposed model is extensively evaluated through multiple document clustering and classification tasks conducted over several large-scale document sets. Evaluation results clearly and consistently demonstrate the effectiveness and superiority of the new model with respect to several state-of-the-art peer models.
Inhalt: Vgl.: http://onlinelibrary.wiley.com/doi/10.1002/asi.23822/full.
10Liu, Y.-H. ; Wacholder, N.: Evaluating the impact of MeSH (Medical Subject Headings) terms on different types of searchers.
In: Information processing and management. 53(2017) no.4, S.851-870.
Abstract: A commonly used technique for improving search engine performance is result caching. In result caching, precomputed results (e.g., URLs and snippets of best matching pages) of certain queries are stored in a fast-access storage. The future occurrences of a query whose results are already stored in the cache can be directly served by the result cache, eliminating the need to process the query using costly computing resources. Although other performance metrics are possible, the main performance metric for evaluating the success of a result cache is hit rate. In this work, we present a machine learning approach to improve the hit rate of a result cache by facilitating a large number of features extracted from search engine query logs. We then apply the proposed machine learning approach to static, dynamic, and static-dynamic caching. Compared to the previous methods in the literature, the proposed approach improves the hit rate of the result cache up to 0.66%, which corresponds to 9.60% of the potential room for improvement.
Inhalt: Vgl.: https://doi.org/10.1016/j.ipm.2017.03.004.
Themenfeld: Verbale Doksprachen für präkombinierte Einträge
11Liu, Y. ; Li, W. ; Huang, Z. ; Fang, Q.: ¬A fast method based on multiple clustering for name disambiguation in bibliographic citations.
In: Journal of the Association for Information Science and Technology. 66(2015) no.3, S.634-644.
Abstract: Name ambiguity in the context of bibliographic citation affects the quality of services in digital libraries. Previous methods are not widely applied in practice because of their high computational complexity and their strong dependency on excessive attributes, such as institutional affiliation, research area, address, etc., which are difficult to obtain in practice. To solve this problem, we propose a novel coarse-to-fine framework for name disambiguation which sequentially employs 3 common and easily accessible attributes (i.e., coauthor name, article title, and publication venue). Our proposed framework is based on multiple clustering and consists of 3 steps: (a) clustering articles by coauthorship and obtaining rough clusters, that is fragments; (b) clustering fragments obtained in step 1 by title information and getting bigger fragments; (c) and clustering fragments obtained in step 2 by the latent relations among venues. Experimental results on a Digital Bibliography and Library Project (DBLP) data set show that our method outperforms the existing state-of-the-art methods by 2.4% to 22.7% on the average pairwise F1 score and is 10 to 100 times faster in terms of execution time.
Inhalt: Vgl.: http://onlinelibrary.wiley.com/doi/10.1002/asi.23183/abstract.
12Liu, Y. ; Rousseau, R.: Citation analysis and the development of science : a case study using articles by some Nobel prize winners.
In: Journal of the Association for Information Science and Technology. 65(2014) no.2, S.281-289.
Abstract: Using citation data of articles written by some Nobel Prize winners in physics, we show that concave, convex, and straight curves represent different types of interactions between old ideas and new insights. These cases illustrate different diffusion characteristics of academic knowledge, depending on the nature of the knowledge in the new publications. This work adds to the study of the development of science and links this development to citation analysis.
13Chen, Y.-L. ; Liu, Y.-H. ; Ho, W.-L.: ¬A text mining approach to assist the general public in the retrieval of legal documents.
In: Journal of the American Society for Information Science and Technology. 64(2013) no.2, S.280-290.
Abstract: Applying text mining techniques to legal issues has been an emerging research topic in recent years. Although some previous studies focused on assisting professionals in the retrieval of related legal documents, they did not take into account the general public and their difficulty in describing legal problems in professional legal terms. Because this problem has not been addressed by previous research, this study aims to design a text-mining-based method that allows the general public to use everyday vocabulary to search for and retrieve criminal judgments. The experimental results indicate that our method can help the general public, who are not familiar with professional legal terms, to acquire relevant criminal judgments more accurately and effectively.
Themenfeld: Data Mining
14Liu, Y. ; Rousseau, R.: Interestingness and the essence of citation : Thomas Reid and bibliographic description.
In: Journal of documentation. 69(2013) no.4, S.580-589.
Abstract: Purpose - This paper aims to provide a new insight into the reasons why authors cite. Design/methodology/approach The authors argue that, based on philosophical ideas about the essence of things, pure rational thinking about the role of citations leads to the answer. Findings - Citations originate from the interestingness of the investigated phenomenon. The essence of citation lies in the interaction between different ideas or perspectives on a phenomenon addressed in the citing as well as in the cited articles. Research limitations/implications - The findings only apply to ethical (not whimsical or self-serving) citations. As such citations reflect interactions of scientific ideas, they can reveal the evolution of science, revive the cognitive process of an investigated scientific phenomenon and reveal political and economic factors influencing the development of science. Originality/value - This article is the first to propose interestingness and the interaction of ideas as the basic reason for citing. This view on citations allows reverse engineering from citations to ideas and hence becomes useful for science policy.
15Hider, P. ; Liu, Y.-H.: ¬The use of RDA elements in support of FRBR user tasks.
In: Cataloging and classification quarterly. 51(2013) no.8, S.857-872.
Abstract: Resource Description and Access (RDA) stipulates that certain "core" elements should always be included, where applicable, in bibliographic and authority records, due to their importance in supporting the user tasks defined in Functional Requirements for Bibliographic Records. However, the elements' relative importance has not been empirically tested. This study investigates which elements in bibliographic records are currently most used in a university library catalog, by means of think-aloud sessions conducted by expert and non-expert users, who were assigned sets of typical bibliographic tasks. The results indicate that, in this context at least, the most utilized elements are not all core.
16Liu, Y. ; Rafols, I. ; Rousseau, R.: ¬A framework for knowledge integration and diffusion.
In: Journal of documentation. 68(2012) no.1, S.31-44.
Abstract: Purpose - This paper aims to introduce a general framework for the analysis of knowledge integration and diffusion using bibliometric data. Design/methodology/approach - The authors propose that in order to characterise knowledge integration and diffusion of a given issue (the source, for example articles on a topic or by an organisation, etc.), one has to choose a set of elements from the source (the intermediary set, for example references, keywords, etc.). This set can then be classified into categories (cats), thus making it possible to investigate its diversity. The set can also be characterised according to the coherence of a network associated to it. Findings - This framework allows a methodology to be developed to assess knowledge integration and diffusion. Such methodologies can be useful for a number of science policy issues, including the assessment of interdisciplinarity in research and dynamics of research networks. Originality/value - The main contribution of this article is to provide a simple and easy to use generalisation of an existing approach to study interdisciplinarity, bringing knowledge integration and knowledge diffusion together in one framework.
17Liu, Y. ; Rousseau, R.: Towards a representation of diffusion and interaction of scientific ideas : the case of fiber optics communication.
In: Information processing and management. 48(2012) no.4, S.791-801.
Abstract: The research question studied in this contribution is how to find an adequate representation to describe the diffusion of scientific ideas over time. We claim that citation data, at least of articles that act as concept symbols, can be considered to contain this information. As a case study we show how the founding article by Nobel Prize winner Kao illustrates the evolution of the field of fiber optics communication. We use a continuous description of discrete citation data in order to accentuate turning points and breakthroughs in the history of this field. Applying the principles explained in this contribution informetrics may reveal the trajectories along which science is developing.
Inhalt: Vgl.: doi:10.1016/j.ipm.2011.12.001.
18Wu, M.M. ; Liu, Y.-H.: On intermediaries' inquiring minds, elicitation styles, and user satisfaction.
In: Journal of the American Society for Information Science and Technology. 62(2011) no.12, S.2396-2403.
Abstract: Building upon previous research on the concepts of inquiring minds and elicitation styles (Wu, 2005; Wu & Liu, 2003), this study aims to identify the relationships between the theoretical constructs of elicitation behavior and user satisfaction in terms of the relevance, utility, and satisfaction of search results, search interaction processes, and overall search activities. Descriptive statistical analysis is applied to compare the user satisfaction ratings with respect to the concepts of inquiring minds and elicitation styles. The results suggest that the stereotyped elicitation style received the lowest user satisfaction ratings compared with functionally and situationally oriented styles. It is suggested that the intermediaries take into account the characteristics of search questions and, accordingly, adapt their professional mindsets to search interview situations; that is, using an inquiring mind in the query formulation process as default mode with functional and situational styles of elicitations would be helpful for enhancing the user's satisfaction ratings. Future research is suggested to better understand and to improve professional talk in information services.
19Lim, S.C.J. ; Liu, Y. ; Lee, W.B.: ¬A methodology for building a semantically annotated multi-faceted ontology for product family modelling.
In: Advanced engineering informatics. 25(2011) no.2, S.147-161.
Abstract: Product family design is one of the prevailing approaches in realizing mass customization. With the increasing number of product offerings targeted at different market segments, the issue of information management in product family design, that is related to an efficient and effective storage, sharing and timely retrieval of design information, has become more complicated and challenging. Product family modelling schema reported in the literature generally stress the component aspects of a product family and its analysis, with a limited capability to model complex inter-relations between physical components and other required information in different semantic orientations, such as manufacturing, material and marketing wise. To tackle this problem, ontology-based representation has been identified as a promising solution to redesign product platforms especially in a semantically rich environment. However, ontology development in design engineering demands a great deal of time commitment and human effort to process complex information. When a large variety of products are available, particularly in the consumer market, a more efficient method for building a product family ontology with the incorporation of multi-faceted semantic information is therefore highly desirable. In this study, we propose a methodology for building a semantically annotated multi-faceted ontology for product family modelling that is able to automatically suggest semantically-related annotations based on the design and manufacturing repository. The six steps of building such ontology: formation of product family taxonomy; extraction of entities; faceted unit generation and concept identification; facet modelling and semantic annotation; formation of a semantically annotated multi-faceted product family ontology (MFPFO); and ontology validation and evaluation are discussed in detail. Using a family of laptop computers as an illustrative example, we demonstrate how our methodology can be deployed step by step to create a semantically annotated MFPFO. Finally, we briefly discuss future research issues as well as interesting applications that can be further pursued based on the MFPFO developed.
20Liu, Y. ; Rousseau, R.: Knowledge diffusion through publications and citations : a case study using ESI-fields as unit of diffusion.
In: Journal of the American Society for Information Science and Technology. 61(2010) no.2, S.340-351.
Abstract: Two forms of diffusion are studied: diffusion by publications, originating from the fact that a group publishes in different fields; and diffusion by citations, originating from the fact that the group's publications are cited in different fields. The first form of diffusion originates from an internal mechanism by which the group itself expands its own borders. The second form is partly driven by an external mechanism, in the sense that other fields use or become interested in the original group's expertise, and partly by the group's internal dynamism, in the sense that their articles, being published in more and more fields, have the potential to be applied in these other fields. In this contribution, we focus on basic counting measures as measures of diffusion. We introduce the notions of field diffusion breadth, defined as the number of for Essential Science Indicators (ESI) fields in which a set of articles is cited, and field diffusion intensity, defined as the number of citing articles in one particular ESI field. Combined effects of publications and citations can be measured by the Gini evenness measure. Our approach is illustrated by a study of mathematics at Tongji University (Shanghai, China).