Noticias em eLiteracias

🔒
❌ Sobre o FreshRSS
Há novos artigos disponíveis, clique para atualizar a página.
Antes de ontemH-I

The double-edged effects of data privacy practices on customer responses

Publication date: April 2023

Source: International Journal of Information Management, Volume 69

Author(s): Shijiao (Joseph) Chen, Khai Trieu Tran, Zhenhua (Raymond) Xia, Donia Waseem, Jing A. Zhang, Balkrushna Potdar

  • 24 de Novembro de 2022, 19:15

Computational metadata generation methods for biological specimen image collections

Abstract

Metadata is a key data source for researchers seeking to apply machine learning (ML) to the vast collections of digitized biological specimens that can be found online. Unfortunately, the associated metadata is often sparse and, at times, erroneous. This paper extends previous research conducted with the Illinois Natural History Survey (INHS) collection (7244 specimen images) that uses computational approaches to analyze image quality, and then automatically generates 22 metadata properties representing the image quality and morphological features of the specimens. In the research reported here, we demonstrate the extension of our initial work to University of the Wisconsin Zoological Museum (UWZM) collection (4155 specimen images). Further, we enhance our computational methods in four ways: (1) augmenting the training set, (2) applying contrast enhancement, (3) upscaling small objects, and (4) refining our processing logic. Together these new methods improved our overall error rates from 4.6 to 1.1%. These enhancements also allowed us to compute an additional set of 17 image-based metadata properties. The new metadata properties provide supplemental features and information that may also be used to analyze and classify the fish specimens. Examples of these new features include convex area, eccentricity, perimeter, skew, etc. The newly refined process further outperforms humans in terms of time and labor cost, as well as accuracy, providing a novel solution for leveraging digitized specimens with ML. This research demonstrates the ability of computational methods to enhance the digital library services associated with the tens of thousands of digitized specimens stored in open-access repositories world-wide by generating accurate and valuable metadata for those repositories.

  • 23 de Novembro de 2022, 00:00

Adapting multilingual speech representation model for a new, underresourced language through multilingual fine-tuning and continued pretraining

Publication date: March 2023

Source: Information Processing & Management, Volume 60, Issue 2

Author(s): Karol Nowakowski, Michal Ptaszynski, Kyoko Murasaki, Jagna Nieuważny

  • 24 de Novembro de 2022, 10:32

Goal-setting in support of learning during search: An exploration of learning outcomes and searcher perceptions

Publication date: March 2023

Source: Information Processing & Management, Volume 60, Issue 2

Author(s): Kelsey Urgo, Jaime Arguello

  • 24 de Novembro de 2022, 10:32

Semantic matching in machine reading comprehension: An empirical study

Publication date: Available online 18 November 2022

Source: Information Processing & Management

Author(s): Qian Liu, Rui Mao, Xiubo Geng, Erik Cambria

  • 24 de Novembro de 2022, 10:32

Editorial Board

Publication date: January 2023

Source: Information Processing & Management, Volume 60, Issue 1

Author(s):

  • 24 de Novembro de 2022, 10:32

Reducing 0s bias in video moment retrieval with a circular competence-based captioner

Publication date: March 2023

Source: Information Processing & Management, Volume 60, Issue 2

Author(s): Guolong Wang, Xun Wu, Zhaoyuan Liu, Zheng Qin

  • 24 de Novembro de 2022, 10:32

Fair and Explainable Depression Detection in Social Media

Publication date: January 2023

Source: Information Processing & Management, Volume 60, Issue 1

Author(s): V Adarsh, P Arun Kumar, V Lavanya, G.R. Gangadharan

  • 24 de Novembro de 2022, 10:32

A deep learning-based expert finding method to retrieve agile software teams from CQAs

Publication date: March 2023

Source: Information Processing & Management, Volume 60, Issue 2

Author(s): Peyman Rostami, Azadeh Shakery

  • 24 de Novembro de 2022, 10:32

Federated reinforcement learning approach for detecting uncertain deceptive target using autonomous dual UAV system

Publication date: March 2023

Source: Information Processing & Management, Volume 60, Issue 2

Author(s): Haythem Bany Salameh, Mohannad Alhafnawi, Ala’eddin Masadeh, Yaser Jararweh

  • 24 de Novembro de 2022, 10:32

AugPrompt: Knowledgeable augmented-trigger prompt for few-shot event classification

Publication date: Available online 18 November 2022

Source: Information Processing & Management

Author(s): Chengyu Song, Fei Cai, Jianming Zheng, Xiang Zhao, Taihua Shao

  • 24 de Novembro de 2022, 10:32

Performance analysis of a private blockchain network built on Hyperledger Fabric for healthcare

Publication date: March 2023

Source: Information Processing & Management, Volume 60, Issue 2

Author(s): Ghassan Al-Sumaidaee, Rami Alkhudary, Zeljko Zilic, Andraws Swidan

  • 24 de Novembro de 2022, 10:32

Exploring developments of the AI field from the perspective of methods, datasets, and metrics

Publication date: March 2023

Source: Information Processing & Management, Volume 60, Issue 2

Author(s): Rujing Yao, Yingchun Ye, Ji Zhang, Shuxiao Li, Ou Wu

  • 24 de Novembro de 2022, 10:32

Data information processing of traffic digital twins in smart cities using edge intelligent federation learning

Publication date: March 2023

Source: Information Processing & Management, Volume 60, Issue 2

Author(s): Weixi Wang, Fan He, Yulei Li, Shengjun Tang, Xiaoming Li, Jizhe Xia, Zhihan Lv

  • 24 de Novembro de 2022, 10:32

Digital transformation and European small and medium enterprises (SMEs): A comparative study using digital economy and society index data

Publication date: February 2023

Source: International Journal of Information Management, Volume 68

Author(s): Marinko Skare, María de las Mercedes de Obesso, Samuel Ribeiro-Navarrete

  • 24 de Novembro de 2022, 10:30

The Effect of Fear and Situational Motivation on Online Information Avoidance: The Case of COVID-19

Publication date: Available online 18 November 2022

Source: International Journal of Information Management

Author(s): Tahmina Sultana, Gurpreet Dhillon, Tiago Oliveira

  • 24 de Novembro de 2022, 10:30

A conceptual model of feedback mechanisms in adjusted affordances – Insights from usage of a mental mobile health application

Publication date: April 2023

Source: International Journal of Information Management, Volume 69

Author(s): Christian Meske, Ireti Amojo, Devinder Thapa

  • 24 de Novembro de 2022, 10:30

General practitioners' wellbeing during the COVID‐19 pandemic: Novel methods with social media data

Por Su Golder, Laura Jefferson, Elizabeth McHugh, Holly Essex, Claire Heathcote, Ana Castro Avila, Veronica Dale, Christina Van Der Feltz‐Cornelis, Karen Bloor

Abstract

Background

It is difficult to engage busy healthcare professionals in research. Yet during the COVID-19 pandemic, gaining their perspectives has never been more important.

Objective

To explore social media data for insights into the wellbeing of UK General Practitioners (GPs) during the Covid-19 pandemic.

Methods

We used a combination of search approaches to identify 381 practising UK NHS GPs on Twitter. Using a two stage social media analysis, we firstly searched for key themes from 91,034 retrieved tweets (before and during the pandemic). Following this we used qualitative content analysis to provide in-depth insights from 7145 tweets related to wellbeing.

Results

Social media proved a useful tool to identify a cohort of UK GPs; following their tweets longitudinally to explore key themes and trends in issues related to GP wellbeing during the pandemic. These predominately related to support, resources and public perceptions and fluctuations were identified at key timepoints during the pandemic, all achieved without burdening busy GPs.

Conclusion

Social media data can be searched to identify a cohort of GPs to explore their wellbeing and changes over time.

The antecedents and consequences of intergroup affective polarisation on social media

Por Robin L. Wakefield, Kirk Wakefield

Abstract

Social media platforms enable like-minded users to form online groups, interact and thereby contribute to ideological polarisation. However, online groups also polarise along a continuum of liking or affect for their group compared to other groups. We explore affective polarisation on social media and its implications for online intergroup interaction. Using social identity theory, we investigate the effects of group identification, passion, and affective polarisation on social media users' intergroup approach and avoidance tendencies. We test the research model in the context of political groups on social media. We find group identification contributes to affective polarisation by strengthening favouritism for the ingroup rather than hostility for the outgroup. Although those with greater group identification prefer to confront (approach) the opposition group on social media, the behaviour is a function of inflated feelings for the ingroup more so than animus for the outgroup. Interestingly, users with greater affective polarisation tend to shut out (avoid) the rival group on social media. Our findings imply affective polarisation contributes to group isolation that may exacerbate ideological polarisation.

A twin data-driven approach for user-experience based design innovation

Publication date: February 2023

Source: International Journal of Information Management, Volume 68

Author(s): Bai Yang, Ying Liu, Wei Chen

  • 17 de Novembro de 2022, 16:19

Publisher’s note

Publication date: September 2022

Source: Information and Organization, Volume 32, Issue 3

Author(s):

  • 17 de Novembro de 2022, 16:18

From coexistence to co-creation: Blurring boundaries in the age of AI

Publication date: December 2022

Source: Information and Organization, Volume 32, Issue 4

Author(s): Lauren Waardenburg, Marleen Huysman

  • 17 de Novembro de 2022, 16:18
❌