Noticias em eLiteracias

🔒
✇ Journal of Web Librarianship

Sustainable enterprise strategies for optimizing digital stewardship

Por John Rodzvilla — 29 de Novembro de 2022, 03:42
.
✇ Journal of Web Librarianship

The culture of digital scholarship in academic libraries

Por Steve Brantley, — 29 de Novembro de 2022, 03:39
.
✇ The Journal of Academic Librarianship

A statistical analysis of the tangible fine art book collection at an academic library

5 de Dezembro de 2022, 10:47

Publication date: March 2023

Source: The Journal of Academic Librarianship, Volume 49, Issue 2

Author(s): Emy Nelson Decker

✇ The Journal of Academic Librarianship

Big data-driven investigation into the maturity of library research data services (RDS)

5 de Dezembro de 2022, 10:47

Publication date: January 2023

Source: The Journal of Academic Librarianship, Volume 49, Issue 1

Author(s): Marek Nahotko, Magdalena Zych, Aneta Januszko-Szakiel, Małgorzata Jaskowska

✇ Journal of Informetrics

Signatures of capacity development through research collaborations in artificial intelligence and machine learning

5 de Dezembro de 2022, 10:47

Publication date: February 2023

Source: Journal of Informetrics, Volume 17, Issue 1

Author(s): Vinayak, Adarsh Raghuvanshi, Avinash kshitij

✇ Knowledge and Information Systems

Improved score aggregation for authorship verification

3 de Dezembro de 2022, 00:00

Abstract

The Impostors method is one of the most successful solvers of author verification problems. Given a pair of texts, it aims to find whether the same author wrote them or not. This paper describes a proposed approach with the primary objective of achieving a higher classification accuracy. This higher accuracy is achieved by modifying the vector representations of input texts, such that the effect of them possibly being in different domains is reduced. Such vector modification factors are obtained by the addition of a computational step that empirically estimates the expected difference, or ratio, between the questioned texts’ similarity scores against their in-domain samples. Our evaluation confirms that our proposed approach is capable of achieving higher classification accuracy than the original method. Despite the size of the evaluation dataset, some of the increases in the classification accuracy are large enough to allow for observing statistically significant, very significant, and highly significant gains.

✇ Knowledge and Information Systems

Advanced agronomics model with species classification, minimum support price prediction, and profit suggestion using enhanced deep learning strategy

2 de Dezembro de 2022, 00:00

Abstract

Minimum support price (MSP) is an advisory price signal, which is a component of a huge collection of agricultural policies in parts of India. The agricultural commodities evaluate the derivatives by noticing the climate changes regarding external factors like economic and weather conditions. The severe changes in these factors result in significant price changes. Here, it may experience more cost-efficiency in analyzing the agricultural species. The problem arises because the mixed species in the single pixel increases the pixel size. The high-dimensional problem of input and outputs occurs in the hyper-spectral data. Hence, this research implements a new MSP method in Agronomics or Agriculture through deep learning algorithms. In the species prediction phase, the input remote sensing images are gathered and processed in pre-processing phase using median filtering and contrast limited adaptive histogram equalization. Here, the pre-processed images are fed to feature extraction using the gray-level co-occurrence matrix (GLCM) and spatial feature extraction techniques. Further, the deep feature extraction is analyzed using convolutional neural network (CNN) by considering the input as the pre-processed images and extracting GLCM and spatial features. These deep features are forwarded to the enhanced recurrent neural-long short-term memory (ERN-LSTM), where the parameters of RNN and LSTM are tuned by self-adaptive dingo optimizer (SA-DOX). Finally, the species prediction outcomes are attained by enhanced RNN + LSTM. Secondly, in the MSP prediction phase, the major aim is to predict the MSP based on the species detected. Here, the gathered price data, along with the extracted CNN-based deep features, are processed to select the significant optimal features and are carried out by the same improved DOX. The selected features are given to enhanced RNN + LSTM for predicting the MSP price related to the crop type. Thirdly, the predicted prices are split into four shares. Fourthly, profit suggestion is carried out by training the location and regional crop data, and thus, the enhanced RNN + LSTM model gives the best profitable harvests. Through the experimental results, the accuracy of species classification using SA-DOX-based ERN-LSTM was 10.9, 8.3, 6.85, and 4.7%, accordingly advanced than SVM, LSTM, RNN, and RNN-LSTM. From the given findings, the better accuracy rate of the given designed method is 96.75%. Accordingly, the better sensitivity and precision rates are 95.9 and 95.5%. Finally, this study explores competitive performance through the experimental results relative to the traditional approaches.

✇ Knowledge and Information Systems

A new method of ensemble learning: case of cryptocurrency price prediction

1 de Dezembro de 2022, 00:00

Abstract

This work proposes a novel method of ensemble learning for time series prediction. Different machine learning-based models have been integrated, and a combined prediction model has been created. The objective of the ensemble model is that it must outperform all other individual models that are used to construct the ensemble model in terms of producing excellent predictions. The field of cryptocurrencies has been selected as the domain of this work where the focus is to predict the cryptocurrency prices using the proposed model. A new regression model is proposed and implemented in this work. Different machine learning techniques have been adopted and integrated to form a combined prediction model. The machine learning models include deep neural networks, support vector regression, and decision trees. The regression scheme has to be implemented on each machine learning model separately as well as their performance is also to be improved. The combined prediction model requires optimal weights generation for integration, and therefore, time complexity is a concern. A large set of experiments have been carried out on various cryptocurrencies and the results are displayed. Real-world data has been used here and a comparison is also performed. It is observed that the combined prediction model outperforms other models resulting in excellent predictions capturing most of the nonstationary movements in the data.

✇ Journal of Business & Finance Librarianship

The oxford handbook of international business strategy, edited by Kamel Mellahi, Klaus Meyer, Rajneesh Narula, Irina Surdu, and Alain Verbeke, Oxford, UK: Oxford University Press, 2021, 519 pp., $102.83, ISBN 978-0198868378

Por Donal Anry Jaya Sinurat — 30 de Novembro de 2022, 12:46
.
✇ Knowledge and Information Systems

Identifying significant textual features in titles of Google play store applications and their influence on user review rating

30 de Novembro de 2022, 00:00

Abstract

User review rating of mobile applications is a crucial factor related to downloads and it greatly impacts the customer’s decisions to prefer the applications with the highest (most positive) ratings. Whereas, titles are among the first information displayed to users when they search for any particular application and a compelling title can be a leading cause for an application’s success. Hence, developer companies fashion (optimize) their application titles strategically, in such a way, that they are highly eye-catching and descriptive about application functionalities in an attempt to lure users to download and positively rate their applications. However, traditional literature may lack the scientific approaches which investigate what (specific) kind of textual features in application titles actually have a positive (or negative) effect on the review rating. Therefore, aim of this research work is to perform two separate kinds of scientific analyses to determine the impacts of unconscious (aspects usually not observed by users) and conscious (keyterms which are observed by users) features of Google-play store application titles on the user review rating. At first, for the investigation of unconscious aspects various machine learning algorithms are employed and secondly, for the conscious features another keyterms analysis is carried out. Overall, according to the results, certain unconscious aspects can lead towards the elevated review ratings in both cases of Applications and Games. Albeit, conscious aspects tend to have a positive impact only on the review ratings of Games.

✇ Knowledge and Information Systems

Automated urban planning aware spatial hierarchies and human instructions

29 de Novembro de 2022, 00:00

Abstract

Traditional urban planning demands urban experts to spend much time producing an optimal urban plan under many architectural constraints. The remarkable imaginative ability of deep generative learning provides hope for renovating this domain. Existing works are constrained by: (1) neglecting human requirements; (2) omitting spatial hierarchies, and (3) lacking urban plan samples. We propose a novel, deep human-instructed urban planner to fill these gaps and implement two practical frameworks. In the preliminary version, we formulate the task into an encoder–decoder paradigm. The encoder is to learn the information distribution of surrounding contexts, human instructions, and land-use configuration. The decoder is to reconstruct the land-use configuration and the associated urban functional zones. Although it has achieved good results, the generation performance is still unstable due to the complex optimization directions of the decoder. Thus, we propose a cascading deep generative adversarial network (GAN) in this paper, inspired by the workflow of urban experts. The first GAN is to build urban functional zones based on human instructions and surrounding contexts. The second GAN will produce the land-use configuration by considering the built urban functional zones. Finally, we conducted extensive experiments and case studies to validate the effectiveness and superiority of our work.

✇ Journal of Informetrics

Hidden scales in statistics of citation indicators

29 de Novembro de 2022, 18:39

Publication date: February 2023

Source: Journal of Informetrics, Volume 17, Issue 1

Author(s): Andrey M. Tokmachev

✇ Journal of Informetrics

Editorial Board

29 de Novembro de 2022, 18:39

Publication date: November 2022

Source: Journal of Informetrics, Volume 16, Issue 4

Author(s):

✇ Journal of Informetrics

Interpretable reparameterisations of citation models

29 de Novembro de 2022, 18:39

Publication date: February 2023

Source: Journal of Informetrics, Volume 17, Issue 1

Author(s): Barbara Żogała-Siudem, Anna Cena, Grzegorz Siudem, Marek Gagolewski

✇ Journal of Informetrics

Global informetric impact: A description and definition using bundles

29 de Novembro de 2022, 18:39

Publication date: February 2023

Source: Journal of Informetrics, Volume 17, Issue 1

Author(s): Leo Egghe, Ronald Rousseau

✇ The Journal of Academic Librarianship

The architecture of academic libraries in Israel: Knowledge and prestige

29 de Novembro de 2022, 18:38

Publication date: March 2023

Source: The Journal of Academic Librarianship, Volume 49, Issue 2

Author(s): Jonathan Letzter

✇ The Journal of Academic Librarianship

Microaggressions in Academic Spaces: What About the Library?

29 de Novembro de 2022, 18:38

Publication date: March 2023

Source: The Journal of Academic Librarianship, Volume 49, Issue 2

Author(s): J.J. Prieto-Gutiérrez, María-Jesús Colmenero-Ruiz

✇ Journal of the American Society for Information Science and Technology

LAGOS‐AND: A large gold standard dataset for scholarly author name disambiguation

Por Li Zhang, Wei Lu, Jinqing Yang — 28 de Novembro de 2022, 09:30

Abstract

In this article, we present a method to automatically build large labeled datasets for the author ambiguity problem in the academic world by leveraging the authoritative academic resources, ORCID and DOI. Using the method, we built LAGOS-AND, two large, gold-standard sub-datasets for author name disambiguation (AND), of which LAGOS-AND-BLOCK is created for clustering-based AND research and LAGOS-AND-PAIRWISE is created for classification-based AND research. Our LAGOS-AND datasets are substantially different from the existing ones. The initial versions of the datasets (v1.0, released in February 2021) include 7.5 M citations authored by 798 K unique authors (LAGOS-AND-BLOCK) and close to 1 M instances (LAGOS-AND-PAIRWISE). And both datasets show close similarities to the whole Microsoft Academic Graph (MAG) across validations of six facets. In building the datasets, we reveal the variation degrees of last names in three literature databases, PubMed, MAG, and Semantic Scholar, by comparing author names hosted to the authors' official last names shown on the ORCID pages. Furthermore, we evaluate several baseline disambiguation methods as well as the MAG's author IDs system on our datasets, and the evaluation helps identify several interesting findings. We hope the datasets and findings will bring new insights for future studies. The code and datasets are publicly available.

✇ Journal of Library Administration

Assessing the Impact of Academic Librarians upon Student Satisfaction through Reference Desk Interactions: A Preliminary Pilot Study

Por P. J. Louderback — 28 de Novembro de 2022, 03:38
Volume 62, Issue 8, November-December 2022, Page 1085-1092
.
✇ Journal of Library Administration

Abandoning Yesterday to Transform Tomorrow

Por Douglas Way — 28 de Novembro de 2022, 03:38
Volume 62, Issue 8, November-December 2022, Page 1070-1076
.
✇ Journal of Library Administration

Understanding Disability to Support Library Workers

Por Katelyn Quirin Manwiller — 28 de Novembro de 2022, 03:38
Volume 62, Issue 8, November-December 2022, Page 1077-1084
.
✇ Knowledge and Information Systems

DNETC: dynamic network embedding preserving both triadic closure evolution and community structures

27 de Novembro de 2022, 00:00

Abstract

Network embedding, a central issue of deep learning preprocessing on social networks, aims to transform network elements (vertices) into low-dimensional latent vector space while preserving the topology and properties of the network. However, most of the existing methods mainly focus on static networks, neglecting the dynamic characteristics of real social networks. The explanation for the fundamental dynamic mechanism of social network evolution is still lacking. We design a novel dynamic network embedding approach preserving both triadic closure evolution and community structures (DNETC). First, three factors, the popularity of vertices, the proximity of vertices, and the community structures, are incorporated relying on the triadic closure principle in social networks. Second, the triadic closure loss function, the community loss function, and the temporal smoothness loss function are constructed and incorporated to optimize DNETC. Finally, the low-dimensional cognition presentation of a dynamic social network can be achieved, which can save both the evolution patterns of microscopic vertices and the structure information of macroscopic communities. Experiments on the classical tasks of link prediction, link reconstruction, and changed link reconstruction and prediction demonstrate the superiority of DNETC over state-of-the-art methods. The first experimental results validate the effectiveness of adopting triadic closure progress and community structures to improve the quality of the learned low-dimensional vectors. The last experimental results further verify the parameter sensitivity of DNETC to the analysis task. It provides a new idea for dynamic network embedding to reflect the real evolution characteristics of networks and enhance the effect of network analysis tasks. The code is available at https://github.com/YangMin-10/DNETC.

✇ Knowledge and Information Systems

Dynamic ensemble selection classification algorithm based on window over imbalanced drift data stream

27 de Novembro de 2022, 00:00

Abstract

Data stream classification is an important research direction in the field of data mining, but in many practical applications, it is impossible to collect the complete training set at one time, and the data may be in an imbalanced state and interspersed with concept drift, which will greatly affect the classification performance. To this end, an online dynamic ensemble selection classification algorithm based on window over imbalanced drift data stream (DESW-ID) is proposed. The algorithm employs various balancing measures, first resampling the data stream using Poisson distribution, and if it is in a highly imbalanced state then secondary sampling is performed using a window storing a minority class instances to achieve the current balanced state of the data. To improve the processing efficiency of the algorithm, a classifier selection ensemble is proposed to dynamically adjust the number of classifiers, and the algorithm runs with an ADWIN detector to detect the presence of concept drift. The experimental results show that the proposed algorithm ranks first on average in all five classification performance metrics compared to the state-of-the-art methods. Therefore, the proposed algorithm has better classification performance for imbalanced data streams with concept drift and also improves the operation efficiency of the algorithm.

✇ Journal of Library & Information Services in Distance Learning

Involuntary Online Learners and the Library: How the Pandemic Closures Affected College Students’ Library Research

Por Tricia Lantzy — 26 de Novembro de 2022, 07:36
.
✇ Journal of Business & Finance Librarianship

Sage research methods core review

Por Georgette Nicolosi — 24 de Novembro de 2022, 01:35
.
❌