Can social media usage of scientific literature predict journal indices of AJG,SNIP and JCR? An altmetric study of economics

Scientometrics - Altmetrics are often praised as an alternative or complement to classic bibliometric metrics, especially in the social sciences discipline. However, empirical investigations of...     

Bibliometric-enhanced information retrieval: a novel deep feature engineering approach for algorithm searching from full-text publications

Scientometrics - Recently, tremendous advances have been observed in information retrieval systems designed to search for relevant knowledge in scientific publications. Although these techniques...     

A decade of in-text citation analysis based on natural language processing and machine learning techniques: an overview of empirical studies

Scientometrics - In-text citation analysis is one of the most frequently used methods in research evaluation. We are seeing significant growth in citation analysis through bibliometric metadata,...     

A bibliometric study of research activity in ASEAN related to the EU in FP7 priority areas

Two relevant recent developments in the area of science and technology (S&T) and related policy-making motivate this article: first, bibliometric data on a specific research area’s performance becomes an increasingly relevant source for S&T policy-making and evaluation. This trend is embedded in wider discussions on evidence-based policy-making. Secondly, the scientific output of Southeast Asian countries is rising, as is the number of international research collaborations with the second area of our interest: Europe. Against this background, we employ basic bibliometric methodology in order to draw a picture of Southeast Asian research strengths as well the amount and focus of S&T cooperation between the countries in Southeast Asia and the European Union. The results can prove useful for an interested public as well as for the scientific community and science, technology and innovation policy-making.     

Influential tweeters in relation to highly cited articles in altmetric big data

Scientometrics - The relationship between influential tweeters and highly cited articles in the field of information sciences was analysed using Twitter data gathered by Altmetric.com from July...     

Measuring recent research performance for Chinese universities using bibliometric methods

This paper focuses on measuring the academic research performance of Chinese universities by using Scopus database from 2007 to 2010. We have provided meaningful indicators to measure the research performance of Chinese universities as compared to world class universities of the US and the European region. Using these indicators, we first measure the quantity and quality of the research outcomes of the universities and then examine the internationalization of research by using international collaborations, international citations and international impact metrics. Using all of this data, we finally present an overall score called research performance point to measure the comprehensive research strength of the universities for the selected subject categories. The comparison identifies the gap between Chinese universities and top-tier universities from selected regions across various subject areas. We find that Chinese universities are doing well in terms of publication volume but receive less citations from their published work. We also find that the Chinese universities have relative low percentage of publications at high impact venues, which may be the reason that they are not receiving more citations. Therefore, a careful selection of publication venues may help the Chinese universities to compete with world class universities and increase their research internationalization.     

Small-world phenomenon of keywords network based on complex network

Based on the network comprised of 111,444 keywords of library and information science that are extracted from Scopus, and taken into consideration the major properties of average distance and clustering coefficients, the present authors, with the knowledge of complex network and by means of calculation, reveal the small-world effect of the keywords network. On the basis of the keywords network, the betweenness centrality is used to carry out a preliminary study on how to detect the research hotspots of a discipline. This method is also compared with that of detecting research hotspots by word frequency.     

Measuring international knowledge flows and scholarly impact of scientific research

We introduce a new quantitative measure of international scholarly impact of countries by using bibliometric techniques based on publication and citation data. We present a case study to illustrate the use of our proposed measure in the subject area Energy during 1996–2009. We also present geographical maps to visualize knowledge flows among countries. Finally, using correlation analysis between publication output and international scholarly impact, we study the explanatory power of the applied measure.     

Robust hybrid name disambiguation framework for large databases

In many databases, science bibliography database for example, name attribute is the most commonly chosen identifier to identify entities. However, names are often ambiguous and not always unique which cause problems in many fields. Name disambiguation is a non-trivial task in data management that aims to properly distinguish different entities which share the same name, particularly for large databases like digital libraries, as only limited information can be used to identify authors’ name. In digital libraries, ambiguous author names occur due to the existence of multiple authors with the same name or different name variations for the same person. Also known as name disambiguation, most of the previous works to solve this issue often employ hierarchical clustering approaches based on information inside the citation records, e.g. co-authors and publication titles. In this paper, we focus on proposing a robust hybrid name disambiguation framework that is not only applicable for digital libraries but also can be easily extended to other application based on different data sources. We propose a web pages genre identification component to identify the genre of a web page, e.g. whether the page is a personal homepage. In addition, we propose a re-clustering model based on multidimensional scaling that can further improve the performance of name disambiguation. We evaluated our approach on known corpora, and the favorable experiment results indicated that our proposed framework is feasible.     

Virtual learning environment to predict withdrawal by leveraging deep learning

The current evolution in multidisciplinary learning analytics research poses significant challenges for the exploitation of behavior analysis by fusing data streams toward advanced decision-making. The identification of students that are at risk of withdrawals in higher education is connected to numerous educational policies, to enhance their competencies and skills through timely interventions by academia. Predicting student performance is a vital decision-making problem including data from various environment modules that can be fused into a homogenous vector to ascertain decision-making. This research study exploits a temporal sequential classification problem to predict early withdrawal of students, by tapping the power of actionable smart data in the form of students' interactional activities with the online educational system, using the freely available Open University Learning Analytics data set by employing deep long short-term memory (LSTM) model. The deployed LSTM model outperforms baseline logistic regression and artificial neural networks by 10.31% and 6.48% respectively with 97.25% learning accuracy, 92.79% precision, and 85.92% recall.