Change search
Link to record
Permanent link

Direct link
BETA
Eklund, Johan
Publications (10 of 13) Show all publications
Eklund, J., Gunnarsson Lorenzen, D. & Nelhans, G. (2019). MESH classification of clinical guidelinesusing conceptual embeddings of references. In: Giuseppe Catalano, Cinzia Daraio, Martina Gregori, Henk F. Moed and Giancarlo Ruocco (Ed.), Proceedings of the 17th conference of the International society for scientometrics and informetrics, ISSI: with a Special STI Indicators Conference Track. Paper presented at 17th conference of the International society for scientometrics and informetrics, ISSI (pp. 859-864). , 2
Open this publication in new window or tab >>MESH classification of clinical guidelinesusing conceptual embeddings of references
2019 (English)In: Proceedings of the 17th conference of the International society for scientometrics and informetrics, ISSI: with a Special STI Indicators Conference Track / [ed] Giuseppe Catalano, Cinzia Daraio, Martina Gregori, Henk F. Moed and Giancarlo Ruocco, 2019, Vol. 2, p. 859-864Conference paper, Published paper (Refereed)
Abstract [en]

In this study, we investigate different strategies for assigning MeSH (Medical Subject Headings) terms to clinical guidelines using machine learning. Features based on words in titles and abstracts are investigated and compared to features based on topics assigned to references cited by the guidelines. Two of the feature engineering strategies utilize word embeddings produced by recent models based on in the distributional hypothesis, called word2vecand fastText. The evaluation results show that reference-based strategies tend to yield a higher recall and F1 scores for MeSH terms with a sufficient amount of training instances, whereas title and abstract based features yield a higher precision.

Keywords
MESH, clinical guidelines, machine learning, word embedding, word2vec, fasttext
National Category
Information Studies
Research subject
Library and Information Science
Identifiers
urn:nbn:se:hb:diva-22096 (URN)978-88-3381-118-5 (ISBN)
Conference
17th conference of the International society for scientometrics and informetrics, ISSI
Projects
Data for Impact
Funder
EU, Horizon 2020, 770531
Available from: 2019-11-22 Created: 2019-11-22 Last updated: 2019-12-06Bibliographically approved
Gunnarsson Lorenzen, D., Eklund, J., Nelhans, G. & Ekström, B. (2019). On the potential for detecting scientific issues and controversies on Twitter: A method for investigation conversations mentioning research. In: Proceedings of ISSI.: . Paper presented at ISSI, the 17th International Conference on Scientometrics & Informetrics, Rome, 2-5 September, 2019. (pp. 2189-2198). , Article ID 375.
Open this publication in new window or tab >>On the potential for detecting scientific issues and controversies on Twitter: A method for investigation conversations mentioning research
2019 (English)In: Proceedings of ISSI., 2019, p. 2189-2198, article id 375Conference paper, Published paper (Refereed)
Abstract [en]

In this study, we demonstrate how to collect Twitter conversations emanating from or referring to scientific papers. We propose segmenting the conversational threads into smaller segments and then compare them using information retrieval techniques, in order to find differences and similarities between discussions and within discussions. While the method still can be improved, the study shows that it is possible to collect larger conversations about research on Twitter, and that these are suitable for various automated methods. We do however identify a need to analyse these with qualitative methods as well.

Keywords
Twitter, conversations
National Category
Computer and Information Sciences
Research subject
Library and Information Science
Identifiers
urn:nbn:se:hb:diva-21908 (URN)
Conference
ISSI, the 17th International Conference on Scientometrics & Informetrics, Rome, 2-5 September, 2019.
Projects
Data4Impact
Available from: 2019-10-31 Created: 2019-10-31 Last updated: 2019-11-05Bibliographically approved
Nelhans, G. & Eklund, J. (2019). Semantic drift of cited references in the medical literature. In: : . Paper presented at 24th Nordic Workshop on Bibliometrics and Research Policy, Reykjavik, 27-28 November, 2019..
Open this publication in new window or tab >>Semantic drift of cited references in the medical literature
2019 (English)Conference paper, Oral presentation with published abstract (Other academic)
Abstract [en]

Adding the semantic content of texts to the study of citations opens for new means of research in the field. Words can be used in specific or more general terms. Their meaning changes through use. Correspondingly, the meaning of a cited reference is defined by its use. Furthermore, the meaning of the reference changes as it is used in different contexts. Using ‘word embeddings’ we create a conceptual space of references using a window of text around the references. The model is trained on a set of 2 million full-text articles derived from EuroPMC. We measure the length of the journey of the cited references in this space to determine how much their semantic meaning changes over time. Furthermore, we study the topical heterogeneity of the citation contexts inferred to the references by the citing documents.

 

  • RQ1. Can we identify the degree of topical heterogeneity of a subset of investigated cited references?
  • RQ2. Can we identify the semantic drift in cited references over time?
  • RQ3. Can we infer the presence of a cited reference in a given text using our trained model? Correspondingly: can we reconstruct the context of a reference in a text?

 

In this explorative work we investigate to what degree the semantic meaning of a cited reference can be recognized. In the end, we explore the possibility to generate a dynamic classification of research based on its use, rather than on their content. This would make it possible to identify similar works irrespectively of manifest citation links (bibliographic coupling or co-citation) or identical content of words (co-word analysis).

Keywords
semantic modelling, citation context
National Category
Information Studies Other Computer and Information Science
Research subject
Library and Information Science
Identifiers
urn:nbn:se:hb:diva-22688 (URN)
Conference
24th Nordic Workshop on Bibliometrics and Research Policy, Reykjavik, 27-28 November, 2019.
Projects
Data for impact
Funder
EU, Horizon 2020, 770531
Available from: 2020-01-28 Created: 2020-01-28 Last updated: 2020-01-31Bibliographically approved
Eklund, J. & Nelhans, G. (2017). Topic modelling approaches to aggregated citation data. In: : . Paper presented at 22nd International Conference on Science and Technology Indicators, Paris, September 6-8, 2017.
Open this publication in new window or tab >>Topic modelling approaches to aggregated citation data
2017 (English)Conference paper, Published paper (Other academic)
Abstract [en]

In this research in progress paper we report on preliminary results from the proposed novel uses of topic modelling approaches to bibliographic references as sources for “bags-of-words” instead of actual text content in scientometric settings. The actual cited references, viewed as concept symbols for paradigmatic approaches to earlier research, could thereby be used to cluster research. We will demonstrate an explorative approach to using cited reference topics for the discovery of hidden semantic reference structures in a set of scientific articles. If found fruitful and robust, this approach could complement existing text based and citation based techniques to clustering of research that might bridge the two approaches. By approaching references as “words” and reference lists as “sentences” (or documents) of such “words”, we demonstrate that the topical structure of document collections can also be analyzed using an alternative and complementary source of content, which additionally provides an interesting perspective on bibliographic references as units of a meta language describing document content.

Keywords
Topic modelling, citation analysis, clinical guidelines, PubMed
National Category
Information Studies Information Systems, Social aspects
Research subject
Library and Information Science
Identifiers
urn:nbn:se:hb:diva-12770 (URN)
Conference
22nd International Conference on Science and Technology Indicators, Paris, September 6-8, 2017
Projects
Professional ImpactTacit
Available from: 2017-09-29 Created: 2017-09-29 Last updated: 2017-10-03Bibliographically approved
Nelhans, G. & Eklund, J. (2016). Citation impact in clinical guidelines. In: : . Paper presented at 21st Nordic Workshop on Bibliometrics and Research Policy, Copenhagen, November 3-4, 2016.
Open this publication in new window or tab >>Citation impact in clinical guidelines
2016 (English)Conference paper, Poster (with or without abstract) (Other academic)
Abstract [en]

In the search to secure funding, researchers must now respond to requests by governments and non-government organisations about how to measure the societal and professional impact of their research. While case studies and reports of interventions may provide grounds for qualitative evaluation, bibliometric methodology is emerging as an important quantitative supplement to these evaluations. 

  In clinical practice, treatment recommendations and clinical guidelines provide traces of clinical and professional practice that can be used to identify and measure research impact. To understand how these traces emerge the research reported here explores documents issued by the three main Swedish agencies who produce recommendations for clinical practice. In particular it examines the cited references within the documents to explore size distribution, reference age, and geographical aspects, in addition to the similarities of the cited reference structure between the producers of the documents.

  The overall goal of this ongoing project is to gain insights into citation practice and distribution of publications in professional practice to provide grounds for developing indicators of clinical impact. Future applications with regard to the broader area of professional impact based on references found in the literature of a wide range of professions, e.g. the health sector, social welfare, engineering and the environmental realm are considered.

Keywords
professional impact, scientometrics, bibliometrics, clinical guidelines
National Category
Other Social Sciences not elsewhere specified
Research subject
Library and Information Science
Identifiers
urn:nbn:se:hb:diva-11140 (URN)10.6084/m9.figshare.4249811.v2 (DOI)
Conference
21st Nordic Workshop on Bibliometrics and Research Policy, Copenhagen, November 3-4, 2016
Projects
Impact i Kliniska Riktlinjer
Available from: 2016-11-15 Created: 2016-11-15 Last updated: 2016-11-24Bibliographically approved
Eklund, J. (2016). With or without context: Automatic text categorization using semantic kernels. (Doctoral dissertation). Högskolan i Borås
Open this publication in new window or tab >>With or without context: Automatic text categorization using semantic kernels
2016 (English)Doctoral thesis, monograph (Other academic)
Abstract [en]

In this thesis text categorization is investigated in four dimensions of analysis: theoretically as well as empirically, and as a manual as well as a machine-based process. In the first four chapters we look at the theoretical foundation of subject classification of text documents, with a certain focus on classification as a procedure for organizing documents in libraries. A working hypothesis used in the theoretical analysis is that classification of documents is a process that involves translations between statements in different languages, both natural and artificial. We further investigate the close relationships between structures in classification languages and the order relations and topological structures that arise from classification.

A classification algorithm that gets a special focus in the subsequent chapters is the support vector machine (SVM), which in its original formulation is a binary classifier in linear vector spaces, but has been extended to handle classification problems for which the categories are not linearly separable. To this end the algorithm utilizes a category of functions called kernels, which induce feature spaces by means of high-dimensional and often non-linear maps. For the empirical part of this study we investigate the classification performance of semantic kernels generated by different measures of semantic similarity. One category of such measures is based on the latent semantic analysis and the random indexing methods, which generates term vectors by using co-occurrence data from text collections. Another semantic measure used in this study is pointwise mutual information. In addition to the empirical study of semantic kernels we also investigate the performance of a term weighting scheme called divergence from randomness, that has hitherto received little attention within the area of automatic text categorization.

The result of the empirical part of this study shows that the semantic kernels generally outperform the “standard” (non-semantic) linear kernel, especially for small training sets. A conclusion that can be drawn with respect to the investigated datasets is therefore that semantic information in the kernel in general improves its classification performance, and that the difference between the standard kernel and the semantic kernels is particularly large for small training sets. Another clear trend in the result is that the divergence from randomness weighting scheme yields a classification performance surpassing that of the common tf-idf weighting scheme.

Place, publisher, year, edition, pages
Högskolan i Borås, 2016. p. 300
Series
Skrifter från Valfrid, ISSN 1103-6990 ; 60
Keywords
automatic text categorization, subject classification, machine learning, computational linguistics, support vector machines, semantic kernels, term weighting, divergence from randomness
National Category
Information Studies
Research subject
Library and Information Science
Identifiers
urn:nbn:se:hb:diva-8949 (URN)978-91-981654-8-7 (ISBN)978-91-981654-9-4 (ISBN)
Public defence
2016-04-15, C203, Allégatan 1, Borås, 13:00
Available from: 2016-02-24 Created: 2016-02-23 Last updated: 2016-03-23Bibliographically approved
Dahlström, M. & Eklund, J. (2011). Litteraturbanken: utvärderingsrapport. Litteraturbanken
Open this publication in new window or tab >>Litteraturbanken: utvärderingsrapport
2011 (Swedish)Report (Other academic)
Place, publisher, year, edition, pages
Litteraturbanken, 2011. p. 78
National Category
Cultural Studies Information Studies General Literature Studies
Research subject
Library and Information Science
Identifiers
urn:nbn:se:hb:diva-4497 (URN)2320/8232 (Local ID)2320/8232 (Archive number)2320/8232 (OAI)
Available from: 2015-12-17 Created: 2015-12-17 Last updated: 2018-01-04Bibliographically approved
Berger, G., Darányi, S., Eklund, J., Hallén, M. & Höglund, L. (2008). Information visualization for product development in the LIVA project. InfoTrend, 63(1), 3-13
Open this publication in new window or tab >>Information visualization for product development in the LIVA project
Show others...
2008 (English)In: InfoTrend, ISSN 1653-0225, Vol. 63, no 1, p. 3-13Article in journal (Other (popular science, discussion, etc.))
Abstract [en]

The LIVA research and development project (2005-2007) was conceived to integrate automatic indexing, automatic categorization, information visualization and information retrieval in library systems managing textual document collections. After a brief overview of some major information visualization methods, the user interface prototype is introduced.

Place, publisher, year, edition, pages
Svensk förening för informationsspecialister, 2008
Keywords
information visualization, liva project, automatic categorization, bibliographic records, automatic indexing, information retrieval, user interface, human-computer interaction, Information visualization, text categorization
National Category
Information Studies
Identifiers
urn:nbn:se:hb:diva-2396 (URN)2320/3503 (Local ID)2320/3503 (Archive number)2320/3503 (OAI)
Note

Sponsorship:

Project funding: KK Stiftelsen

Available from: 2015-11-13 Created: 2015-11-13
Samuelsson, Y., Täckström, O., Velupillai, S., Eklund, J., Fišel, M. & Saers, M. (2008). Mixing and blending syntactic and semantic dependencies. In: Alexander Clark, Kristina Toutanova (Ed.), CoNLL '08 Proceedings of the Twelfth Conference on Computational Natural Language Learning: . Paper presented at Twelfth Conference on Computational Natural Language Learning, Manchester, UK, August 16-17, 2008 (pp. 248-252). Manchester, UK
Open this publication in new window or tab >>Mixing and blending syntactic and semantic dependencies
Show others...
2008 (English)In: CoNLL '08 Proceedings of the Twelfth Conference on Computational Natural Language Learning / [ed] Alexander Clark, Kristina Toutanova, Manchester, UK, 2008, p. 248-252Conference paper, Published paper (Refereed)
Abstract [en]

Our system for the CoNLL 2008 shared task uses a set of individual parsers, a set of stand-alone semantic role labellers, and a joint system for parsing and semantic role labelling, all blended together. The system achieved a macro averaged labelled F1-score of 79.79 (WSJ 80.92, Brown 70.49) for the overall task. The labelled attachment score for syntactic dependencies was 86.63 (WSJ 87.36, Brown 80.77) and the labelled F1-score for semantic dependencies was 72.94 (WSJ 74.47, Brown 60.18).

Place, publisher, year, edition, pages
Manchester, UK: , 2008
National Category
General Language Studies and Linguistics
Identifiers
urn:nbn:se:hb:diva-21085 (URN)
Conference
Twelfth Conference on Computational Natural Language Learning, Manchester, UK, August 16-17, 2008
Available from: 2019-05-28 Created: 2019-05-28 Last updated: 2019-06-17Bibliographically approved
Darányi, S. & Eklund, J. (2007). Automated text categorization of bibliographic records. Svensk biblioteksforskning, 16(2), 1-14
Open this publication in new window or tab >>Automated text categorization of bibliographic records
2007 (English)In: Svensk biblioteksforskning, ISSN 0284-4354, E-ISSN 1653-5235, Vol. 16, no 2, p. 1-14Article in journal (Refereed) Published
Place, publisher, year, edition, pages
Högskolan i Borås, 2007
National Category
Information Studies
Identifiers
urn:nbn:se:hb:diva-2266 (URN)2320/2812 (Local ID)2320/2812 (Archive number)2320/2812 (OAI)
Available from: 2015-11-13 Created: 2015-11-13 Last updated: 2017-09-04Bibliographically approved
Organisations

Search in DiVA

Show all publications