Claire François

New classification quality estimators for analysis of documentary information: application to patent analysis and web mapping

The information analysis process includes a cluster analysis or classification step associated with an expert validation of the results. In this paper, we propose new measures of Recall/Precision for estimating the quality of cluster analysis. These measures derive both from the Galois lattice theory and from the Information Retrieval (IR) domain. As opposed to classical measures of inertia, they present the main advantages to be both independent of the classification method and of the difference between the intrinsic dimension of the data and those of the clusters. We present two experiments on the basis of the MultiSOM model, which is an extension of Kohonens SOM model, as a cluster analysis method. Our first experiment on patent data shows how our measures can be used to compare viewpoint-oriented classification methods, such as MultiSOM, with global cluster analysis method, such as WebSOM. Our second experiment, which takes part in the EICSTES EEC project, is an original Webometrics experiment that combines content and links classification starting from a large non-homogeneous set of web pages. This experiment highlights the fact that break-even points between our different measures of Recall/Precision can be used to determine an optimal number of clusters for web data classification. The content of the clusters obtained when using different break-even points are compared for determining the quality of the resulting maps.

Using artificial neural networks for mapping of scienceand technology: A multi-self-organizing-maps approach

We argue in favour of artificial neural networks for exploratory data analysis, clustering andmapping. We propose the Kohonen self-organizing map (SOM) for clustering and mappingaccording to a multi-maps extension. It is consequently called Multi-SOM. Firstly the KohonenSOM algorithm is presented. Then the following improvements are detailed: the way of namingthe clusters, the map division into logical areas, and the map generalization mechanism. Themulti-map display founded on the inter-maps communication mechanism is exposed, and thenotion of the viewpoint is introduced. The interest of Multi-SOM is presented for visualization,exploration or browsing, and moreover for scientific and technical information analysis. A casestudy in patent analysis on transgenic plants illustrates the use of the Multi-SOM. We also showthat the inter-map communication mechanism provides support for watching the plants on whichpatented genetic technology works. It is the first map. The other four related maps provideinformation about the plant parts that are concerned, the target pathology, the transgenictechniques used for making these plants resistant, and finally the firms involved in geneticengineering and patenting. A method of analysis is also proposed in the use of this computerbasedmulti-maps environment. Finally, we discuss some critical remarks about the proposedapproach at its current state. And we conclude about the advantages that it provides for aknowledge-oriented watching analysis on science and technology. In relation with this remark weintroduce in conclusion the notion of knowledge indicators.

An advanced diffusion model to identify emergent research issues: the case of optoelectronic devices

Scientific progress in technology oriented research fields is made by incremental or fundamental inventions concerning natural science effects, materials, methods, tools and applications. Therefore our approach focuses on research activities of such technological elements on the basis of keywords in published articles. In this paper we show how emerging topics in the field of optoelectronic devices based on scientific literature data from the PASCAL-database can be identified. We use Results from PROMTECH project, whose principal objective was to produce a methodology allowing the identification of promising emerging technologies. In this project, the study of the intersection of Applied Sciences as well as Life (Biological & Medical) Sciences domains and Physics with bibliometric methods produced 45 candidate technological fields and the validation by expert panels led to a final selection of 10 most promising ones. These 45 technologies were used as reference fields. In order to detect the emerging research, we combine two methodological approaches. The first one introduces a new modelling of field terminology evolution based on bibliometric indicators: the diffusion model and the second one is a diachronic cluster analysis. With the diffusion model we identified single keywords that represent a high dynamic of the mentioned technology elements. The cluster analysis was used to recombine articles, where the identified keywords were used to technological topics in the field of optoelectronic devices. This methodology allows us to answer the following questions: Which technological aspects within our considered field can be detected? Which of them are already established and which of them are new? How are the topics linked to each other?

Identification and characterisation of technological topics in the field of Molecular Biology

Following up the European project PromTech the aim of which was to detect emerging technologies by studying the scientific literature, we chose one field, Molecular Biology, to identify and characterize emerging topics within that domain. We combined two analytical approaches: the first one introduces a model of the terminological evolution of the field based on bibliometric indicators and the second one operates a diachronic clustering analysis. Our objective is to bring answers to questions such as: Which technological aspects can be detected? Which of them are already established and which of them are new? How are the topics linked to each other?

Artificial neural network technology for the classification and cartography of scientific and technical information

This paper describes the implementation of multivariate data analysis: NEURODOC applies the axial k-means method for automatic, non-hierarchical cluster analysis and a Principal Component Analysis (PCA) for representing the clusters on a map. We next introduce Artificial Neural Networks (ANNs) to extend NEURODOC into a neural platform for the cluster analysis and cartography of bibliographic data. The ANNs tested are: the Adaptive Resonance Theory (ART 1), a Multilayer Perceptron (MLP), and an associative network with unsupervised learning (KOHONEN). This platform is intended for quantitative analysis of information.

Using a compound approach based on elaborated neural network for Webometrics: An example issued from the EICSTES project

This paper present a compound approach for Webometrics based on an extension the self-organizing multimap MultiSOM model. The goal of this new approach is to combine link and domain clustering in order to increase the reliability and the precision of Webometrics studies. The extension proposed for the MultiSOM model is based on a Bayesian network-oriented approach. A first experiment shows that the behaviour of such an extension is coherent with its expected properties for Webometrics. A second experiment is carried out on a representative Web dataset issued from the EISCTES IST project context. In this latter experiment each map represents a particular viewpoint extracted from the Web data description. The obtained maps represented either thematic or link classifications. The experiment shows empirically that the communication between these classifications provides Webometrics with new explaining capabilities.

Enhancing Patent Expertise through Automatic Matching with Scientific Papers

This paper focuses on a subtask of the QUAERO research program, a major innovating research project related to the automatic processing of multimedia and multilingual content. The objective discussed in this article is to propose a new method for the classification of scientific papers, developed in the context of an international patents classification plan related to the same field. The practical purpose of this work is to provide an assistance tool to experts in their task of evaluation of the originality and novelty of a patent, by offering to the latter the most relevant scientific citations. This issue raises new challenges in categorization research as the patent classification plan is not directly adapted to the structure of scientific documents, classes have high citation or cited topic and that there is not always a balanced distribution of the available examples within the different learning classes. We propose, as a solution to this problem, to apply an improved K-nearest-neighbors (KNN) algorithm based on the exploitation of association rules occurring between the index terms of the documents and the ones of the patent classes. By using a reference dataset of patents belonging to the field of pharmacology, on the one hand, and a bibliographic dataset of the same field issued from the Medline collection, on the other hand, we show that this new approach, which combines the advantages of numerical and symbolical approaches, improves considerably categorization performance, as compared to the usual categorization methods.

A concept for inferring `frontier research' in grant proposals

This paper discusses a concept for inferring attributes of ‘frontier research’ in peer-reviewed research proposals under the popular scheme of the European Research Council (ERC). The concept serves two purposes: firstly to conceptualize, define and operationalize in scientometric terms attributes of frontier research; and secondly to build and compare outcomes of a statistical model with the review decision in order to obtain further insight and reflect upon the influence of frontier research in the peer-review process. To this end, indicators across scientific disciplines and in accord with the strategic definition of frontier research by the ERC are elaborated, exploiting textual proposal information and other scientometric data of grant applicants. Subsequently, a suitable model is formulated to measure ex-post the influence of attributes of frontier research on the decision probability of a proposal to be accepted. We present first empirical data as proof of concept for inferring frontier research in grant proposals. Ultimately the concept is aiming at advancing the methodology to deliver signals for monitoring the effectiveness of peer-review processes.

Exploring the bibliometric and semantic nature of negative results

Negative results are not popular to disseminate. However, their publication would help to save resources and foster scientific communication. This study analysed the bibliometric and semantic nature of negative results publications. The Journal of Negative Results in Biomedicine (JNRBM) was used as a role model. Its complete articles from 2002–2009 were extracted from SCOPUS and supplemented by related records. Complementary negative results records were retrieved from Web of Science in “Biochemistry” and “Telecommunications”. Applied bibliometrics comprised of co-author and co-affiliation analysis and a citation impact profile. Bibliometrics showed that authorship is widely spread. A specific community for the publication of negative results in devoted literature is non-existent. Neither co-author nor co-affiliation analysis indicated strong interconnectivities. JNRBM articles are cited by a broad spectrum of journals rather than by specific titles. Devoted negative results journals like JNRBM have a rather low impact measured by the number of received citations. On the other hand, only one-third of the publications remain uncited, corroborating their importance for the scientific community. The semantic analysis relies on negative expressions manually identified in JNRBM article titles and abstracts and extracted to syntactic patterns. By using a Natural Language Processing tool these patterns are then employed to detect their occurrences in the multidisciplinary bibliographical database PASCAL. The translation of manually identified negation patterns to syntactic patterns and their application to multidisciplinary bibliographic databases (PASCAL, Web of Science) proved to be a successful method to retrieve even hidden negative results. There is proof that negative results are not only restricted to the biomedical domain. Interestingly a high percentage of the so far identified negative results papers were funded and therefore needed to be published. Thus policies that explicitly encourage or even mandate the publication of negative results could probably bring about a shift in the current scientific communication behaviour.

For Visualization-Based Analysis Tools in Knowledge Discovery Process: A Multilayer Perceptron versus Principal Components Analysis: A Comparative Study

Mapping knowledge structures is a key task in Knowledge Discovery in Databases (KDD). In order to display the thematic organization of knowledge, we compare and evaluate two different cartography approaches: principal components analysis (PCA) and a multilayer perceptron (MLP) in “self-association” mode. This kind of MLP can be used to perform a PCA when the activation function is set to the identity function. This allows us to look for the non-linear activation function which best fits the data structure. We present an evaluation criterion and the results and maps obtained with both methods. We notice that the MLP detects a non-linearity in the data structure that the PCA does not detect. However, the MLP does not express the non-linearity completely. Finally we show how a related component analysis (RCA), based on graph theory, provides representations of the inter-clusters relationships, compensating for the approximate nature of the maps, and improving their readability.