Predicting scientific research trends based on link prediction in keyword networks

Research Ideas Discovery via Hierarchical Negative Correlation

A new research idea may be inspired by the connections of keywords. Link prediction discovers potential nonexisting links in an existing graph and has been applied in many applications. This article explores a method of discovering new research ideas based on link prediction, which predicts the possible connections of different keywords by analyzing the topological structure of the keyword graph. The patterns of links between keywords may be diversified due to different domains and different habits of authors. Therefore, it is often difficult for a single learner to extract diverse patterns of different research domains. To address this issue, groups of learners are organized with negative correlation to encourage the diversity of sublearners. Moreover, a hierarchical negative correlation mechanism is proposed to extract subgraph features in different order subgraphs, which improves the diversity by explicitly supervising the negative correlation on each layer of sublearners. Experiments are conducted to illustrate the effectiveness of the proposed model to discover new research ideas. Under the premise of ensuring the performance of the model, the proposed method consumes less time and computational cost compared with other ensemble methods.

Machine learning prediction of academic collaboration networks

We investigate the different roles played by nodes' network and non-network attributes in explaining the formation of European university collaborations from 2011 to 2016, in three European Research Council (ERC) domains: Social Sciences and Humanities (SSH), Physical and Engineering Sciences (PE), Life Sciences (LS), as well as multidisciplinary collaborations. On link formation in collaboration networks, existing research has not yet compared and simultaneously examined both network and non-network attributes. Using four machine learning predictive algorithms (LASSO, Neural Network, Gradient Boosting, and Random Forest) our results show that, over various model specifications: (i) best model link formation accuracy is larger than 80%, (ii) among the non-network attributes, public funding plays an important role in PE and LS, (iii) network attributes count more than non-network attributes for the formation, sensibly increasing accuracy, (iv) feature-importance scores show a different ordering in the four domains, thus signalling different modes of knowledge production and transmission taking place within these different scientific communities.

A review of the knowledge of reef fish in the Southwest Atlantic

Reef environments are rapidly transforming worldwide, and these changes are causing major impacts to the reef ecosystem. Scientific knowledge is strategic for marine conservation and management in these scenarios. Aiming to contribute to this subject, a systematic review from 1967 to 2020 was conducted, in order to identify gaps in studies regarding reef fish species, ecosystem components and processes. Multidisciplinary sciences concerning reef fish have been rising, mainly in the fields of basic biology and ecology. Besides that, phase shifts and ecosystem services were absent terms in the analyzes of co-occurrence. Research in the ethnosciences needs to be increased, and will improve access to local ecological knowledge, which can be used as a tool to address issues in reef environments. Socio-ecological systems are components of this landscape that has had few publications. The participation in the elaboration of public policies can be a new avenue to foster the biodiversity of reef environments.

Science Forum: How failure to falsify in high-volume science contributes to the replication crisis

The number of scientific papers published every year continues to increase, but scientific knowledge is not progressing at the same rate. Here we argue that a greater emphasis on falsification – the direct testing of strong hypotheses – would lead to faster progress by allowing well-specified hypotheses to be eliminated. We describe an example from neuroscience where there has been little work to directly test two prominent but incompatible hypotheses related to traumatic brain injury. Based on this example, we discuss how building strong hypotheses and then setting out to falsify them can bring greater precision to the clinical neurosciences, and argue that this approach could be beneficial to all areas of science.

Cover papers of top journals are reliable source for emerging topics detection: a machine learning based prediction framework

The detection of emerging trends is of great interest to many stakeholders such as government and industry. Previous research focused on the machine learning, network analysis and time series analysis based on the bibliometrics data and made a promising progress. However, these approaches inevitably have time delay problems. For the reason that leader papers of “emerging topics” share the similar characters with the “cover papers”, this study present a novel approach to translate the “emerging topics” detection to “cover paper” prediction. By using “AdaBoost model” and topic model, we construct a machine learning framework to imitate the top journal (chief) editor’s judgement to select cover paper from material science. The results of our prediction were validated by consulting with field experts. This approach was also suitable for the Nature, Science, and Cell journals.

A Normalized Rich-Club Connectivity-Based Strategy for Keyword Selection in Social Media Analysis

In this paper, we present a study on keyword selection behavior in social media analysis that is focused on particular topics, and propose a new effective strategy that considers the co-occurrence relationships between keywords and uses graph-based techniques. In particular, we used the normalized rich-club connectivity considering the weighted degree, closeness centrality, betweenness centrality and PageRank values to measure a subgroup of highly connected “rich keywords” in a keyword co-occurrence network. Community detection is subsequently applied to identify several keyword combinations that are able to accurately and comprehensively represent the researched topic. The empirical results based on four topics and comparing four existing models confirm the performance of our proposed strategy in promoting the quantity and ensuing the quality of data related to particular topics collected from social media. Overall, our findings are expected to offer useful guidelines on how to select keywords for social media-based studies and thus further increase the reliability and validity of their respective conclusions.