Pub Date : 2024-03-05DOI: 10.1177/01655515241233741
Matheus Albergaria
The present article describes recent developments related to the study of libraries in the field of economics. In terms of scope, there is considerable variation in economic applications, with research themes ranging from cost–benefit analyses to the impacts of libraries on educational outcomes, for example. In terms of approaches, the vast majority of articles in the field correspond to empirical studies employing library data, although there is some variation in terms of aggregation. In general, a first look at this burgeoning literature divides its main contributions into two broad sets: (1) one focused on the long-term effects of public libraries over economic outcomes and (2) another focused on the use of libraries as naturally occurring laboratories for the test of economic theories. Although there is not a common theme underlying the majority of contributions here surveyed, there are still sizable opportunities for economists – and social scientists, in general – who want to explore the research potential of libraries.
{"title":"The economics of libraries","authors":"Matheus Albergaria","doi":"10.1177/01655515241233741","DOIUrl":"https://doi.org/10.1177/01655515241233741","url":null,"abstract":"The present article describes recent developments related to the study of libraries in the field of economics. In terms of scope, there is considerable variation in economic applications, with research themes ranging from cost–benefit analyses to the impacts of libraries on educational outcomes, for example. In terms of approaches, the vast majority of articles in the field correspond to empirical studies employing library data, although there is some variation in terms of aggregation. In general, a first look at this burgeoning literature divides its main contributions into two broad sets: (1) one focused on the long-term effects of public libraries over economic outcomes and (2) another focused on the use of libraries as naturally occurring laboratories for the test of economic theories. Although there is not a common theme underlying the majority of contributions here surveyed, there are still sizable opportunities for economists – and social scientists, in general – who want to explore the research potential of libraries.","PeriodicalId":54796,"journal":{"name":"Journal of Information Science","volume":"12 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140046743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-05DOI: 10.1177/01655515231220167
Osman Imoro, Nampombe Saurombe
Institutional repositories (IRs) are increasingly gaining prominence among African academic institutions, and Ghana is no exception. This can largely be attributed to the enduring value of hosting research outputs from institutional and individual depositors. Despite its increasing adoption, there is a growing concern about the sustainability of open access IRs, particularly in Africa. However, most of these factors that threaten the sustainability of IRs on the continent can be mitigated by enacting comprehensive institutional policies. Thus, this study sought to examine the role of institutional policies in the sustainability of IRs in Ghana. A total of 830 respondents comprised of IR managers, library staff, postgraduate students, lecturers and university librarians (management) from five public universities in Ghana took part in this study. Questionnaires, semi-structured interviews and document analysis were the main instruments used for data collection. The study yielded an overall response rate of 92.8%. The study findings revealed that public universities in Ghana have institutional IR policies that guide the operation, usage and management of their IRs. However, these policies were persuasive in nature and mainly focused on content submission and generation issues. The study underscored the IR policy’s importance in addressing content generation, awareness, advocacy and copyright restriction challenges. The study recommends the necessity of IR policies to focus on other factors such as technical requirements, expertise and others to ensure the sustainability of these repositories.
{"title":"The role of institutional policies in the sustainability of institutional repositories in Africa: A reflection from Ghana","authors":"Osman Imoro, Nampombe Saurombe","doi":"10.1177/01655515231220167","DOIUrl":"https://doi.org/10.1177/01655515231220167","url":null,"abstract":"Institutional repositories (IRs) are increasingly gaining prominence among African academic institutions, and Ghana is no exception. This can largely be attributed to the enduring value of hosting research outputs from institutional and individual depositors. Despite its increasing adoption, there is a growing concern about the sustainability of open access IRs, particularly in Africa. However, most of these factors that threaten the sustainability of IRs on the continent can be mitigated by enacting comprehensive institutional policies. Thus, this study sought to examine the role of institutional policies in the sustainability of IRs in Ghana. A total of 830 respondents comprised of IR managers, library staff, postgraduate students, lecturers and university librarians (management) from five public universities in Ghana took part in this study. Questionnaires, semi-structured interviews and document analysis were the main instruments used for data collection. The study yielded an overall response rate of 92.8%. The study findings revealed that public universities in Ghana have institutional IR policies that guide the operation, usage and management of their IRs. However, these policies were persuasive in nature and mainly focused on content submission and generation issues. The study underscored the IR policy’s importance in addressing content generation, awareness, advocacy and copyright restriction challenges. The study recommends the necessity of IR policies to focus on other factors such as technical requirements, expertise and others to ensure the sustainability of these repositories.","PeriodicalId":54796,"journal":{"name":"Journal of Information Science","volume":"6 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140046770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-04DOI: 10.1177/01655515241228224
Ming Zhu, Han Su, Longxiao Niu
This study investigates the settlement information practices of ethnic minorities with small populations (EMSPs) who were relocated to poverty-alleviation areas in Yunnan, China. Data were gathered using interviews and surveys. A face-to-face survey was administered to 126 and 147 EMSPs before and after relocation, respectively, focusing on their information needs, acquisition, and sharing. In addition, in-depth interviews were conducted with 16 relocated EMSP participants to identify the factors influencing their settlement information practices. This study’s findings showed that ethnic characteristics, spatial reconstruction and social inclusion were the primary factors affecting the context of changing living spaces and social communication relationships. Furthermore, the results contribute to a conceptual framework for the settlement information practices of EMSPs and provide valuable insights for research on settlement information practices of newcomer populations across cultures and ethnicities.
{"title":"A ‘field transformation and social integration’: Settlement information practices of relocated ethnic minorities with small populations in poverty-alleviation areas of Yunnan, China","authors":"Ming Zhu, Han Su, Longxiao Niu","doi":"10.1177/01655515241228224","DOIUrl":"https://doi.org/10.1177/01655515241228224","url":null,"abstract":"This study investigates the settlement information practices of ethnic minorities with small populations (EMSPs) who were relocated to poverty-alleviation areas in Yunnan, China. Data were gathered using interviews and surveys. A face-to-face survey was administered to 126 and 147 EMSPs before and after relocation, respectively, focusing on their information needs, acquisition, and sharing. In addition, in-depth interviews were conducted with 16 relocated EMSP participants to identify the factors influencing their settlement information practices. This study’s findings showed that ethnic characteristics, spatial reconstruction and social inclusion were the primary factors affecting the context of changing living spaces and social communication relationships. Furthermore, the results contribute to a conceptual framework for the settlement information practices of EMSPs and provide valuable insights for research on settlement information practices of newcomer populations across cultures and ethnicities.","PeriodicalId":54796,"journal":{"name":"Journal of Information Science","volume":"250 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140034642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-21DOI: 10.1177/01655515241227532
Qingqing Li, Zi Ming Zeng, Shouqiang Sun, Ting ting Li, Yingqi Zeng
To detect multiple coexisting emotions from public emergency opinions, this article proposes a novel two-stage multiple coexisting emotion-detection model. First, the text semantic feature extracted through bidirectional encoder representation from transformers (BERT) and the emotion lexicon feature extracted through the emotion dictionary are fused. Then, the emotion subjectivity judgement and multiple coexisting emotion detection are performed in two separate stages. In the first stage, we introduce synthetic minority oversampling technique (SMOTE) to enhance the balance of data distribution and select the optimal classifier to recognise opinion texts with emotion. In the second stage, the label powerset (LP)-SMOTE is proposed to increase the number of the minority category samples, and multichannel emotion classifiers and the decision mechanism are employed to recognise different types of emotions and determine the final coexisting emotion labels. Finally, the Weibo data about coronavirus disease 2019 (COVID-19) are collected to verify the effectiveness of the proposed model. Experiment results indicate that the proposed model outperforms state-of-the-art models, with the F1_macro of 0.8532, the F1_micro of 0.8333, and the hamming loss of 0.0476. The emotion detection results are conducive to decision-making for public emergency departments.
{"title":"Detecting multiple coexisting emotions from public emergency opinions","authors":"Qingqing Li, Zi Ming Zeng, Shouqiang Sun, Ting ting Li, Yingqi Zeng","doi":"10.1177/01655515241227532","DOIUrl":"https://doi.org/10.1177/01655515241227532","url":null,"abstract":"To detect multiple coexisting emotions from public emergency opinions, this article proposes a novel two-stage multiple coexisting emotion-detection model. First, the text semantic feature extracted through bidirectional encoder representation from transformers (BERT) and the emotion lexicon feature extracted through the emotion dictionary are fused. Then, the emotion subjectivity judgement and multiple coexisting emotion detection are performed in two separate stages. In the first stage, we introduce synthetic minority oversampling technique (SMOTE) to enhance the balance of data distribution and select the optimal classifier to recognise opinion texts with emotion. In the second stage, the label powerset (LP)-SMOTE is proposed to increase the number of the minority category samples, and multichannel emotion classifiers and the decision mechanism are employed to recognise different types of emotions and determine the final coexisting emotion labels. Finally, the Weibo data about coronavirus disease 2019 (COVID-19) are collected to verify the effectiveness of the proposed model. Experiment results indicate that the proposed model outperforms state-of-the-art models, with the F1_macro of 0.8532, the F1_micro of 0.8333, and the hamming loss of 0.0476. The emotion detection results are conducive to decision-making for public emergency departments.","PeriodicalId":54796,"journal":{"name":"Journal of Information Science","volume":"52 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139954851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-19DOI: 10.1177/01655515231216019
Ying Feng, Shanshan Zhang, Xiaoyang Sun
Government social media (GSM) has become an important tool for government departments to open information, guide public opinion and interact with the government and the people. However, the operation and maintenance of some GSM are not standardised, and the content published is inconsistent with identity positioning, resulting in the realistic dilemma of low utility of GSM information. The purpose of this study is to explore the effective strategies to improve the effectiveness of GSM information. The research is from the perspective of information economics, this article uses evolutionary game theory to build a tripartite evolutionary game model comprising GSM operations departments, government regulators and users in order to explore the evolution process of tripartite game behaviours and the influence of subject behaviour selection on information utility. It subsequently conducts a solution and numerical simulation to demonstrate the influence of different factors on the game results. The experimental results show that there are four situations in which the utility of GSM information affects the evolution and stability strategy of the subject and that changes in different parameter values have significant effects on the results of the three-party game. The evolution trend of the subject behaviour can be changed by increasing the regulatory means of rewards and punishments and establishing an efficient operation mechanism for GSM, thus promoting system convergence to the ideal state. The results of this study can provide references and suggestions for government departments to effectively enhance the effectiveness of GSM information and promote the healthy development of GSM.
{"title":"Research on the strategy for improving the utility of government social media information based on a multi-agent game model","authors":"Ying Feng, Shanshan Zhang, Xiaoyang Sun","doi":"10.1177/01655515231216019","DOIUrl":"https://doi.org/10.1177/01655515231216019","url":null,"abstract":"Government social media (GSM) has become an important tool for government departments to open information, guide public opinion and interact with the government and the people. However, the operation and maintenance of some GSM are not standardised, and the content published is inconsistent with identity positioning, resulting in the realistic dilemma of low utility of GSM information. The purpose of this study is to explore the effective strategies to improve the effectiveness of GSM information. The research is from the perspective of information economics, this article uses evolutionary game theory to build a tripartite evolutionary game model comprising GSM operations departments, government regulators and users in order to explore the evolution process of tripartite game behaviours and the influence of subject behaviour selection on information utility. It subsequently conducts a solution and numerical simulation to demonstrate the influence of different factors on the game results. The experimental results show that there are four situations in which the utility of GSM information affects the evolution and stability strategy of the subject and that changes in different parameter values have significant effects on the results of the three-party game. The evolution trend of the subject behaviour can be changed by increasing the regulatory means of rewards and punishments and establishing an efficient operation mechanism for GSM, thus promoting system convergence to the ideal state. The results of this study can provide references and suggestions for government departments to effectively enhance the effectiveness of GSM information and promote the healthy development of GSM.","PeriodicalId":54796,"journal":{"name":"Journal of Information Science","volume":"26 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139954848","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Health information engagement can help individuals to find and use reliable sources of health information to make informed decisions about their health. This helps to improve their health outcomes and prevent unnecessary healthcare costs. Drawing upon the cognitive behavioural theory, this pilot study postulated a model to understand that the consequences of information orientation in terms of information engagement (behaviour), information literacy (cognition) and information avoidance (behaviour) in post-COVID era under health context. Furthermore, the moderation effects of health information literacy (HIL) are also calculated in managing health information avoidance beahvior. This pilot study is conducted in the context of social media exposure to health information by diabetic patients in Pakistani community. The proposed model was tested using Partial Lease Square Structural Equational Modelling (PLS-SEM). The data were collected from 166 diabetic patients (active social media users) through a survey. The study findings suggest that health information orientation on social media leads to HIL and engagement. Whereas, it has significant negative impact towards health information avoidance behaviour. Furthermore, HIL significantly increases health information engagement of diabetic patients. Also, HIL moderates the relationship between health information orientation and information engagement positively, whereas between health information orientation and health information avoidance negatively.
{"title":"Assessing the impact of health information orientation and health information literacy on patients’ engagement with health information","authors":"Ferhana Saeed Hashmi, Saira Hanif Soroya, Khalid Mahmood","doi":"10.1177/01655515241227871","DOIUrl":"https://doi.org/10.1177/01655515241227871","url":null,"abstract":"Health information engagement can help individuals to find and use reliable sources of health information to make informed decisions about their health. This helps to improve their health outcomes and prevent unnecessary healthcare costs. Drawing upon the cognitive behavioural theory, this pilot study postulated a model to understand that the consequences of information orientation in terms of information engagement (behaviour), information literacy (cognition) and information avoidance (behaviour) in post-COVID era under health context. Furthermore, the moderation effects of health information literacy (HIL) are also calculated in managing health information avoidance beahvior. This pilot study is conducted in the context of social media exposure to health information by diabetic patients in Pakistani community. The proposed model was tested using Partial Lease Square Structural Equational Modelling (PLS-SEM). The data were collected from 166 diabetic patients (active social media users) through a survey. The study findings suggest that health information orientation on social media leads to HIL and engagement. Whereas, it has significant negative impact towards health information avoidance behaviour. Furthermore, HIL significantly increases health information engagement of diabetic patients. Also, HIL moderates the relationship between health information orientation and information engagement positively, whereas between health information orientation and health information avoidance negatively.","PeriodicalId":54796,"journal":{"name":"Journal of Information Science","volume":"39 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139954967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-14DOI: 10.1177/01655515241227531
Kadhim Hayawi, Sakib Shahriar, Sujith Samuel Mathew
The potential of artificial intelligence (AI)-based large language models (LLMs) holds considerable promise in revolutionising education, research and practice. However, distinguishing between human-written and AI-generated text has become a significant task. This article presents a comparative study, introducing a novel dataset of human-written and LLM-generated texts in different genres: essays, stories, poetry and Python code. We employ several machine learning models to classify the texts. Results demonstrate the efficacy of these models in discerning between human and AI-generated text, despite the dataset’s limited sample size. However, the task becomes more challenging when classifying GPT-generated text, particularly in story writing. The results indicate that the models exhibit superior performance in binary classification tasks, such as distinguishing human-generated text from a specific LLM, compared with the more complex multiclass tasks that involve discerning among human-generated and multiple LLMs. Our findings provide insightful implications for AI text detection, while our dataset paves the way for future research in this evolving area.
{"title":"The imitation game: Detecting human and AI-generated texts in the era of ChatGPT and BARD","authors":"Kadhim Hayawi, Sakib Shahriar, Sujith Samuel Mathew","doi":"10.1177/01655515241227531","DOIUrl":"https://doi.org/10.1177/01655515241227531","url":null,"abstract":"The potential of artificial intelligence (AI)-based large language models (LLMs) holds considerable promise in revolutionising education, research and practice. However, distinguishing between human-written and AI-generated text has become a significant task. This article presents a comparative study, introducing a novel dataset of human-written and LLM-generated texts in different genres: essays, stories, poetry and Python code. We employ several machine learning models to classify the texts. Results demonstrate the efficacy of these models in discerning between human and AI-generated text, despite the dataset’s limited sample size. However, the task becomes more challenging when classifying GPT-generated text, particularly in story writing. The results indicate that the models exhibit superior performance in binary classification tasks, such as distinguishing human-generated text from a specific LLM, compared with the more complex multiclass tasks that involve discerning among human-generated and multiple LLMs. Our findings provide insightful implications for AI text detection, while our dataset paves the way for future research in this evolving area.","PeriodicalId":54796,"journal":{"name":"Journal of Information Science","volume":"2015 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139955084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-08DOI: 10.1177/01655515231214980
M. Jabeen
The study investigated the adoption footprints of Koha in university libraries in Pakistan by using the Unified Theory of Acceptance and Use of Technology (UTAUT) model. The UTAUT model suggests that the decision to use technology is influenced by performance expectancy, effort expectancy, social influence and facilitating conditions. The study used a survey questionnaire to collect data from 250 librarians working in libraries and analysed the results using a quantitative research approach. The findings of the study revealed that performance expectancy, effort expectancy and facilitating conditions positively influenced the intention to adopt Koha. Interestingly, social influence had no significant effect on the adoption of Koha, indicating that the opinions of others did not play a significant role in the decision to adopt Koha. Personal innovativeness had a negative impact on the behavioural intention of librarians to use Koha. Personal innovativeness refers to the willingness of individuals to adopt new technology, and this finding suggests that librarians who are less willing to adopt new technology may be less probably to adopt Koha. The study also found that the significance of information and communication technology (ICT) background among librarians in Pakistan was low. This can be attributed to inadequate perceived social influence and facilitating conditions towards adopting new information technology (IT) solutions. To increase the use of Koha among librarians, the study recommends that libraries improve social influence and provide better conditions for adoption. This study has important implications for library managers and policymakers who are seeking to enhance the use of open-source library management system (LMS) in university libraries.
本研究采用技术接受和使用统一理论（UTAUT）模型，调查了巴基斯坦大学图书馆采用 Koha 的情况。UTAUT模型认为，使用技术的决定受性能预期、努力预期、社会影响和便利条件的影响。该研究使用调查问卷收集了 250 名图书馆员的数据，并使用定量研究方法对结果进行了分析。研究结果表明，绩效预期、努力预期和便利条件对采用 Koha 的意愿有积极影响。有趣的是，社会影响对 Koha 的采用没有显著影响，这表明他人的意见在决定采用 Koha 的过程中没有发挥重要作用。个人创新性对图书馆员使用 Koha 的行为意向有负面影响。个人创新能力指的是个人采用新技术的意愿，这一结果表明，不太愿意采用新技术的图书馆员可能不太可能采用 Koha。研究还发现，巴基斯坦图书馆员对信息与传播技术（ICT）背景的重视程度较低。这可归因于对采用新信息技术（IT）解决方案的社会影响和有利条件认识不足。为了提高 Koha 在图书馆员中的使用率，研究建议图书馆提高社会影响力，为采用 Koha 提供更好的条件。本研究对图书馆管理者和政策制定者在大学图书馆推广使用开源图书馆管理系统（LMS）具有重要意义。
{"title":"The adoption footprints of Koha as a library management system in university libraries of Pakistan","authors":"M. Jabeen","doi":"10.1177/01655515231214980","DOIUrl":"https://doi.org/10.1177/01655515231214980","url":null,"abstract":"The study investigated the adoption footprints of Koha in university libraries in Pakistan by using the Unified Theory of Acceptance and Use of Technology (UTAUT) model. The UTAUT model suggests that the decision to use technology is influenced by performance expectancy, effort expectancy, social influence and facilitating conditions. The study used a survey questionnaire to collect data from 250 librarians working in libraries and analysed the results using a quantitative research approach. The findings of the study revealed that performance expectancy, effort expectancy and facilitating conditions positively influenced the intention to adopt Koha. Interestingly, social influence had no significant effect on the adoption of Koha, indicating that the opinions of others did not play a significant role in the decision to adopt Koha. Personal innovativeness had a negative impact on the behavioural intention of librarians to use Koha. Personal innovativeness refers to the willingness of individuals to adopt new technology, and this finding suggests that librarians who are less willing to adopt new technology may be less probably to adopt Koha. The study also found that the significance of information and communication technology (ICT) background among librarians in Pakistan was low. This can be attributed to inadequate perceived social influence and facilitating conditions towards adopting new information technology (IT) solutions. To increase the use of Koha among librarians, the study recommends that libraries improve social influence and provide better conditions for adoption. This study has important implications for library managers and policymakers who are seeking to enhance the use of open-source library management system (LMS) in university libraries.","PeriodicalId":54796,"journal":{"name":"Journal of Information Science","volume":"18 17","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139445332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Social media platforms are critical for disaster communication and relief efforts. Rapid and precise social media post analysis is required for effective disaster response. This article presents a comprehensive study of a framework that combines crowdsourcing and text mining techniques to enhance data extraction from social media. The research focuses on a particular case study of COVID-19 pandemic medical supply request, which shows several key findings. First, the incorporation of domain-specific data during the training of named entity recognition (NER) models is essential for accurately identifying and retrieving important entities, such as the names of medical supplies and hospitals. Second, the implementation of a hybrid system leads to improvement in the extraction of information from social media posts. Finally, the involvement of crowdsourcing is found to be significant in the validation, verification, and filtering of disorganised information within the hybrid system. Our performance analysis demonstrates that the use of hybrid models has the potential to significantly improve the extraction of supply names (by up to 37%) and hospital names (by up to 66%), especially in the absence of a comprehensive vocabulary or specially trained NER models. During the COVID-19 supply shortage in Thailand, volunteers utilised hybrid models to expedite the identification of the necessary information. Experiment results demonstrated significant improvement in the accuracy of extracted data, the ability to acquire relevant information in real-time, the capacity to handle a substantial number of posts and the practical benefit of the proposed framework.
社交媒体平台对于灾难沟通和救援工作至关重要。要有效地应对灾难，就必须对社交媒体帖子进行快速而精确的分析。本文全面研究了一个结合众包和文本挖掘技术的框架，以加强从社交媒体中提取数据的能力。研究重点关注 COVID-19 大流行病医疗供应请求这一特殊案例，并得出了几项重要发现。首先，在训练命名实体识别（NER）模型时纳入特定领域的数据对于准确识别和检索重要实体（如医疗用品和医院名称）至关重要。其次，混合系统的实施改进了从社交媒体帖子中提取信息的工作。最后，在混合系统中，众包的参与在验证、核实和过滤杂乱信息方面发挥了重要作用。我们的性能分析表明，使用混合模型有可能显著提高供应品名称（最高提高 37%）和医院名称（最高提高 66%）的提取率，尤其是在缺乏综合词汇或经过专门训练的 NER 模型的情况下。在泰国 COVID-19 供应短缺期间，志愿者利用混合模型加快了必要信息的识别。实验结果表明，所提取数据的准确性、实时获取相关信息的能力、处理大量帖子的能力以及所建议框架的实用性都得到了显著提高。
{"title":"Utilising crowdsourcing and text mining to enhance information extraction from social media: A case study in handling COVID-19 supply requests in Thailand","authors":"Prapaporn Rattanatamrong, Yutthana Boonpalit, Manassanan Boonnavasin","doi":"10.1177/01655515231220164","DOIUrl":"https://doi.org/10.1177/01655515231220164","url":null,"abstract":"Social media platforms are critical for disaster communication and relief efforts. Rapid and precise social media post analysis is required for effective disaster response. This article presents a comprehensive study of a framework that combines crowdsourcing and text mining techniques to enhance data extraction from social media. The research focuses on a particular case study of COVID-19 pandemic medical supply request, which shows several key findings. First, the incorporation of domain-specific data during the training of named entity recognition (NER) models is essential for accurately identifying and retrieving important entities, such as the names of medical supplies and hospitals. Second, the implementation of a hybrid system leads to improvement in the extraction of information from social media posts. Finally, the involvement of crowdsourcing is found to be significant in the validation, verification, and filtering of disorganised information within the hybrid system. Our performance analysis demonstrates that the use of hybrid models has the potential to significantly improve the extraction of supply names (by up to 37%) and hospital names (by up to 66%), especially in the absence of a comprehensive vocabulary or specially trained NER models. During the COVID-19 supply shortage in Thailand, volunteers utilised hybrid models to expedite the identification of the necessary information. Experiment results demonstrated significant improvement in the accuracy of extracted data, the ability to acquire relevant information in real-time, the capacity to handle a substantial number of posts and the practical benefit of the proposed framework.","PeriodicalId":54796,"journal":{"name":"Journal of Information Science","volume":"4 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139380820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-18DOI: 10.1177/01655515231214997
W. Castilhos, M. Macedo-Rouet, Luisa Massarani, C. Almeida
In this qualitative study, 41 adolescents from Brazil and France were asked to conduct web-based searches for science-related information. Different search contexts and current socio-scientific issues were used in order to represent a variety of situations that adolescents are confronted with in their everyday life. Subsequently, they were interviewed about their individual searches. We sought to answer three questions: (a) What types of sources do Brazilian and French adolescents access in their searches? (b) Which evaluation criteria do they use to select the sources they access? (c) Do their source choices differ according to the search context? The results reveal that, regardless of search context, the participants demonstrated trust in news sources, and mistrust towards official sources, mostly as a function of the topic. Receiver-related criteria were particularly relevant for the Brazilian adolescents when selecting the sources, while the French participants based their choices more on parameters related to the content. Results suggest how previous knowledge and interest on the topic can influence teenagers’ choices.
{"title":"Between trust and mistrust: Source evaluation behaviours of Brazilian and French adolescents searching for scientific information on the Web","authors":"W. Castilhos, M. Macedo-Rouet, Luisa Massarani, C. Almeida","doi":"10.1177/01655515231214997","DOIUrl":"https://doi.org/10.1177/01655515231214997","url":null,"abstract":"In this qualitative study, 41 adolescents from Brazil and France were asked to conduct web-based searches for science-related information. Different search contexts and current socio-scientific issues were used in order to represent a variety of situations that adolescents are confronted with in their everyday life. Subsequently, they were interviewed about their individual searches. We sought to answer three questions: (a) What types of sources do Brazilian and French adolescents access in their searches? (b) Which evaluation criteria do they use to select the sources they access? (c) Do their source choices differ according to the search context? The results reveal that, regardless of search context, the participants demonstrated trust in news sources, and mistrust towards official sources, mostly as a function of the topic. Receiver-related criteria were particularly relevant for the Brazilian adolescents when selecting the sources, while the French participants based their choices more on parameters related to the content. Results suggest how previous knowledge and interest on the topic can influence teenagers’ choices.","PeriodicalId":54796,"journal":{"name":"Journal of Information Science","volume":" 16","pages":""},"PeriodicalIF":2.4,"publicationDate":"2023-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138963424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：