Pub Date : 2023-05-26DOI: 10.1177/01655515231176649
Ronyt Gomez, Avshalom Elmalech
Human–computer interaction (HCI) researchers and practitioners have explored how computers and software can aid users in decision-making. Accurate information is crucial in decision-making; therefore, when designing a management information system (MIS), it is necessary to understand the information needs of the end-users and to incorporate this understanding in a way which allows the users to obtain an accurate and intuitive snapshot of the data. Although most of the day-to-day decisions in various organisations are made by middle management employees (as opposed to executives and senior managers), previous literature has scarcely examined how middle management employees’ decision-making process can be improved through the use of MIS. In this study, we examine the impact of different data summarisation and visualisation layouts on different aspects of the decision-making process taking into consideration the decision-makers’ personal characteristics, and propose to include the results of this examination in the MIS design. To this end, we recruited participants from a crowdsourcing platform. Participants were required to complete a task which simulates middle management employees’ day-to-day operational decision-making scenario. To better understand the effects of participants’ personal characteristics and their visual abilities, participants were asked to answer a personality questionnaire and a questionnaire testing for visual abilities. The results indicate that when looking at the population as a single group, the effect of the data summarisation and visualisation layouts on the decision-making process cannot be discerned. However, when taking into consideration additional user characteristics, the results indicate that the data summarisation and visualisation layouts affect the decisions made.
{"title":"Empowering the middle management: Incorporating data summarisation and visualisation techniques in management information systems","authors":"Ronyt Gomez, Avshalom Elmalech","doi":"10.1177/01655515231176649","DOIUrl":"https://doi.org/10.1177/01655515231176649","url":null,"abstract":"Human–computer interaction (HCI) researchers and practitioners have explored how computers and software can aid users in decision-making. Accurate information is crucial in decision-making; therefore, when designing a management information system (MIS), it is necessary to understand the information needs of the end-users and to incorporate this understanding in a way which allows the users to obtain an accurate and intuitive snapshot of the data. Although most of the day-to-day decisions in various organisations are made by middle management employees (as opposed to executives and senior managers), previous literature has scarcely examined how middle management employees’ decision-making process can be improved through the use of MIS. In this study, we examine the impact of different data summarisation and visualisation layouts on different aspects of the decision-making process taking into consideration the decision-makers’ personal characteristics, and propose to include the results of this examination in the MIS design. To this end, we recruited participants from a crowdsourcing platform. Participants were required to complete a task which simulates middle management employees’ day-to-day operational decision-making scenario. To better understand the effects of participants’ personal characteristics and their visual abilities, participants were asked to answer a personality questionnaire and a questionnaire testing for visual abilities. The results indicate that when looking at the population as a single group, the effect of the data summarisation and visualisation layouts on the decision-making process cannot be discerned. However, when taking into consideration additional user characteristics, the results indicate that the data summarisation and visualisation layouts affect the decisions made.","PeriodicalId":54796,"journal":{"name":"Journal of Information Science","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43417415","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 : 2023-05-25DOI: 10.1177/01655515231174384
Maurice Schleußinger, Preben Hansen, R. Ramberg
Recently, virtual reality (VR) technology has become more widespread. Humans increasingly interact with information in VR, and a detailed look into those activities is warranted. Thus, a scoping literature review (PRISMA-ScR) is conducted. It overviews all relevant literature about information-seeking behaviour in VR, focusing on existing models and theories. Out of 536 publications, 37 qualify for this review. Eight publications show an understanding related to information behaviour theories from information science. Pressingly, no publications relate models, frameworks or general theories of information seeking to VR. This review overviews VR-related cognitive and behavioural human factors based on this research gap. Those factors include immersion and presence, affordances, embodiment, cognitive load, human error, flow and engagement. The review is concluded with an explorative framework for future research that is constructed with Marchionini’s process model of information seeking as a baseline and in conjunction with the discussed human factors.
{"title":"Immersive information seeking–A scoping review of information seeking in virtual reality environments","authors":"Maurice Schleußinger, Preben Hansen, R. Ramberg","doi":"10.1177/01655515231174384","DOIUrl":"https://doi.org/10.1177/01655515231174384","url":null,"abstract":"Recently, virtual reality (VR) technology has become more widespread. Humans increasingly interact with information in VR, and a detailed look into those activities is warranted. Thus, a scoping literature review (PRISMA-ScR) is conducted. It overviews all relevant literature about information-seeking behaviour in VR, focusing on existing models and theories. Out of 536 publications, 37 qualify for this review. Eight publications show an understanding related to information behaviour theories from information science. Pressingly, no publications relate models, frameworks or general theories of information seeking to VR. This review overviews VR-related cognitive and behavioural human factors based on this research gap. Those factors include immersion and presence, affordances, embodiment, cognitive load, human error, flow and engagement. The review is concluded with an explorative framework for future research that is constructed with Marchionini’s process model of information seeking as a baseline and in conjunction with the discussed human factors.","PeriodicalId":54796,"journal":{"name":"Journal of Information Science","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46273491","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 : 2023-05-25DOI: 10.1177/01655515231176650
T. Dehdarirad, M. Schirone
This study aimed to compare retracted (due to misconduct) and non-retracted articles in biochemistry, in terms of proportion of positive terms, certainty score and different certainty aspects. The data set of this study composed of 662 retracted and non-retracted articles published in the time period of 2018–2020 and indexed in Scopus. These 662 articles accounted for 331 non-retracted and 331 retracted articles, which were matched using matching and covariate balancing analysis. The analysis in this article was done using several regression models. Regarding the use of positive terms, the findings showed that retracted articles were 16% less probable to use positive terms in abstracts, titles and findings presented in conclusion and discussion compared with non-retracted articles. In addition, the results regarding the analysis of certainty language, showed that retracted articles were 15% less probable to use certain language, measured by certainty score, in presenting their scientific findings. Finally, regarding the certainty aspects, the results of regression models showed that retracted articles had 11% less likelihood to present their research findings using certain probability aspect.
{"title":"Use of positive terms and certainty language in retracted and non-retracted articles: The case of biochemistry","authors":"T. Dehdarirad, M. Schirone","doi":"10.1177/01655515231176650","DOIUrl":"https://doi.org/10.1177/01655515231176650","url":null,"abstract":"This study aimed to compare retracted (due to misconduct) and non-retracted articles in biochemistry, in terms of proportion of positive terms, certainty score and different certainty aspects. The data set of this study composed of 662 retracted and non-retracted articles published in the time period of 2018–2020 and indexed in Scopus. These 662 articles accounted for 331 non-retracted and 331 retracted articles, which were matched using matching and covariate balancing analysis. The analysis in this article was done using several regression models. Regarding the use of positive terms, the findings showed that retracted articles were 16% less probable to use positive terms in abstracts, titles and findings presented in conclusion and discussion compared with non-retracted articles. In addition, the results regarding the analysis of certainty language, showed that retracted articles were 15% less probable to use certain language, measured by certainty score, in presenting their scientific findings. Finally, regarding the certainty aspects, the results of regression models showed that retracted articles had 11% less likelihood to present their research findings using certain probability aspect.","PeriodicalId":54796,"journal":{"name":"Journal of Information Science","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47004941","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 : 2023-05-17DOI: 10.1177/01655515231171086
J. Eykens, Raf Guns, Tim C. E. Engels, Frédéric Vandermoere
This study presents knowledge diffusion analyses for researchers who have been active in the social sciences and humanities. We compare a network based on switches between the main disciplinary classifications of the documents authored throughout their careers to a discipline similarity network. We find that researchers are not exclusively switching between disciplines that are most similar cognitively. Only less than a third of the authors do not switch between disciplines. On the level of the individual researchers, we also study how the cognitive distance travelled relates to boundary crossing. The cognitive distance authors travel is approximated by calculating cosine distances between the vectors of title records for different periods of activity. Moving to new disciplines is found to be positively related to the cognitive distance an author travels throughout her career. Increased specialisation leading to different types of disciplinary boundary work is suggested as a potential explanation for this finding.
{"title":"Cognitive and interdisciplinary mobility in the social sciences and humanities: Traces of increased boundary crossing","authors":"J. Eykens, Raf Guns, Tim C. E. Engels, Frédéric Vandermoere","doi":"10.1177/01655515231171086","DOIUrl":"https://doi.org/10.1177/01655515231171086","url":null,"abstract":"This study presents knowledge diffusion analyses for researchers who have been active in the social sciences and humanities. We compare a network based on switches between the main disciplinary classifications of the documents authored throughout their careers to a discipline similarity network. We find that researchers are not exclusively switching between disciplines that are most similar cognitively. Only less than a third of the authors do not switch between disciplines. On the level of the individual researchers, we also study how the cognitive distance travelled relates to boundary crossing. The cognitive distance authors travel is approximated by calculating cosine distances between the vectors of title records for different periods of activity. Moving to new disciplines is found to be positively related to the cognitive distance an author travels throughout her career. Increased specialisation leading to different types of disciplinary boundary work is suggested as a potential explanation for this finding.","PeriodicalId":54796,"journal":{"name":"Journal of Information Science","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2023-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42562186","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}
Authors often ask how long the peer review process takes. Peer review duration has attracted much attention in academia in recent years. Existing research focuses primarily on the statistical characteristics of peer review duration, with few studies considering the potential influence of manuscripts’ attractiveness. This study aims to fill this research gap by employing attention economy theory. By analysing the peer review history of articles published in The British Medical Journal and 16 information and library science journals, we find a significant negative relationship between peer review duration and the Altmetric Attention Score. Overall, our study offers a new perspective on peer review behaviour and bridges the divide between peer reviews and altmetrics.
{"title":"Is peer review duration shorter for attractive manuscripts?","authors":"Guangyao Zhang, Furong Shang, Lili Wang, Weixi Xie, Pengfei Jia, Chunlin Jiang, Xianwen Wang","doi":"10.1177/01655515231174382","DOIUrl":"https://doi.org/10.1177/01655515231174382","url":null,"abstract":"Authors often ask how long the peer review process takes. Peer review duration has attracted much attention in academia in recent years. Existing research focuses primarily on the statistical characteristics of peer review duration, with few studies considering the potential influence of manuscripts’ attractiveness. This study aims to fill this research gap by employing attention economy theory. By analysing the peer review history of articles published in The British Medical Journal and 16 information and library science journals, we find a significant negative relationship between peer review duration and the Altmetric Attention Score. Overall, our study offers a new perspective on peer review behaviour and bridges the divide between peer reviews and altmetrics.","PeriodicalId":54796,"journal":{"name":"Journal of Information Science","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2023-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41704476","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 : 2023-05-16DOI: 10.1177/01655515231174387
Jundong Zhang, Jia-lin Hou
This article studies the effect of online social media on knowledge diffusion. In this article, an SIS (Susceptible–Infectious–Susceptible) model was established to chase the knowledge diffusion and identify the proper model for knowledge diffusion of individual literature from the perspective of Altmetrics. Based on the data collected from the PLoS ONE database, the transition probabilities of each paper were calculated, and the papers were divided into six groups according to the transition probabilities using a K-means algorithm. This article explores the impacts of transition probabilities and summarises the similarities and differences of the patterns of knowledge diffusion of each group from the perspective of Altmetrics. Research results showed that the SIS model could be used to describe the knowledge diffusion of individual literature from the perspective of Altmetrics. Besides, the classification method proposed in this article could also be applied in future informetric research. In addition, this article also contributes to the practitioners of knowledge diffusion and online platforms.
{"title":"Knowledge diffusion for individual literature from the perspective of Altmetrics: Models, measurement and features","authors":"Jundong Zhang, Jia-lin Hou","doi":"10.1177/01655515231174387","DOIUrl":"https://doi.org/10.1177/01655515231174387","url":null,"abstract":"This article studies the effect of online social media on knowledge diffusion. In this article, an SIS (Susceptible–Infectious–Susceptible) model was established to chase the knowledge diffusion and identify the proper model for knowledge diffusion of individual literature from the perspective of Altmetrics. Based on the data collected from the PLoS ONE database, the transition probabilities of each paper were calculated, and the papers were divided into six groups according to the transition probabilities using a K-means algorithm. This article explores the impacts of transition probabilities and summarises the similarities and differences of the patterns of knowledge diffusion of each group from the perspective of Altmetrics. Research results showed that the SIS model could be used to describe the knowledge diffusion of individual literature from the perspective of Altmetrics. Besides, the classification method proposed in this article could also be applied in future informetric research. In addition, this article also contributes to the practitioners of knowledge diffusion and online platforms.","PeriodicalId":54796,"journal":{"name":"Journal of Information Science","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2023-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42384680","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 : 2023-05-13DOI: 10.1177/01655515231171366
Jeeyoung Yoon, Ji-Hong Park
Scholarly impact has been investigated with great enthusiasm. Scholarly activity has been understood to be accumulative, as Isaac Newton’s famous quote – stand on the giant’s shoulder– indicates, and citation reflects such act of knowledge accumulation and development. While citation count is indeed a robust indicator for academic assessment, given the accumulative and back-to-back nature of academic work, is limited since it does not take descending activities of a paper into consideration. This study suggests a novel approach, the Depth Analysis, which scrutinises descending papers – papers that stood on the giant’s shoulder. Also, novel Depth-based paper assessment method and knowledge structure analysis approach are presented. To validate the method, a case study on conference papers in neural computing domain is conducted. The study result shows that Depth Analysis can capture diachronic scholarly impact and knowledge structure shift more thoroughly.
{"title":"Depth analysis: What happens after papers stand on the giant’s shoulder?","authors":"Jeeyoung Yoon, Ji-Hong Park","doi":"10.1177/01655515231171366","DOIUrl":"https://doi.org/10.1177/01655515231171366","url":null,"abstract":"Scholarly impact has been investigated with great enthusiasm. Scholarly activity has been understood to be accumulative, as Isaac Newton’s famous quote – stand on the giant’s shoulder– indicates, and citation reflects such act of knowledge accumulation and development. While citation count is indeed a robust indicator for academic assessment, given the accumulative and back-to-back nature of academic work, is limited since it does not take descending activities of a paper into consideration. This study suggests a novel approach, the Depth Analysis, which scrutinises descending papers – papers that stood on the giant’s shoulder. Also, novel Depth-based paper assessment method and knowledge structure analysis approach are presented. To validate the method, a case study on conference papers in neural computing domain is conducted. The study result shows that Depth Analysis can capture diachronic scholarly impact and knowledge structure shift more thoroughly.","PeriodicalId":54796,"journal":{"name":"Journal of Information Science","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2023-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41758595","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 : 2023-05-11DOI: 10.1177/01655515231174381
Chuer Xu, Qianjin Zong
Research findings have been widely used as evidence for policy-making. The internationalisation of research activities has been increasing in recent decades, particularly during the COVID-19 pandemic. Previous studies have revealed that international research collaboration can enhance the academic impact of research. However, the effects that international research collaboration exerts on the policy impact of research are still unknown. This study aims to examine the effects of international research collaboration on the policy impact of research (as measured by the number of citations in policy documents) using a causal inference approach. Research articles published by the journal Lancet between 2000 and 2019 were selected as the study sample ( n = 6098). The number of policy citations of each article was obtained from Overton, the largest database of policy citations. Propensity score matching analysis, which takes a causal inference approach, was used to examine the dataset. Four other matching methods and alternative datasets of different sizes were used to test the robustness of the results. The results of this study reveal that international research collaboration has significant and positive effects on the policy impact of research ( coefficient = 4.323, p < 0.001). This study can provide insight to researchers, research institutions and grant funders for improving the policy impact of research.
{"title":"The effects of international research collaboration on the policy impact of research: A causal inference drawing on the journal Lancet","authors":"Chuer Xu, Qianjin Zong","doi":"10.1177/01655515231174381","DOIUrl":"https://doi.org/10.1177/01655515231174381","url":null,"abstract":"Research findings have been widely used as evidence for policy-making. The internationalisation of research activities has been increasing in recent decades, particularly during the COVID-19 pandemic. Previous studies have revealed that international research collaboration can enhance the academic impact of research. However, the effects that international research collaboration exerts on the policy impact of research are still unknown. This study aims to examine the effects of international research collaboration on the policy impact of research (as measured by the number of citations in policy documents) using a causal inference approach. Research articles published by the journal Lancet between 2000 and 2019 were selected as the study sample ( n = 6098). The number of policy citations of each article was obtained from Overton, the largest database of policy citations. Propensity score matching analysis, which takes a causal inference approach, was used to examine the dataset. Four other matching methods and alternative datasets of different sizes were used to test the robustness of the results. The results of this study reveal that international research collaboration has significant and positive effects on the policy impact of research ( coefficient = 4.323, p < 0.001). This study can provide insight to researchers, research institutions and grant funders for improving the policy impact of research.","PeriodicalId":54796,"journal":{"name":"Journal of Information Science","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2023-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41499874","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 : 2023-05-09DOI: 10.1177/01655515231171367
Wenjun Zhao, Kai Meng, Li Sun, Jinhui Ma, Zeguang Jia
The rise of social question and answer (Q&A) platforms has changed the model of traditional health-information services. The quality of answers on a Q&A platform is critical to attract users and increase their community engagement. Thus, recognition of the answer was used to measure users’ acceptance of the answer. A theoretical model of the impact of language style on community recognition of health questions was developed. Nearly 1330 answers from a health question from Zhihu were obtained to verify the model. Results showed that personality reliability, assertiveness, argumentation clarity, commitment, and reverse incentive of health information positively affected answer recognition, while argumentation structure negatively affected answer acceptance. Simultaneously, the degree of use of medical terminology has a significant moderating effect on the relationship between answer recognition and assertiveness, argumentation structure, argumentation clarity, and commitment. Introducing Aristotle’s rhetoric theory to language style and answer recognition could potentially develop healthy communities and disseminate health knowledge.
{"title":"Language style and recognition of the answers in health Q&A community: Moderating effects of medical terminology","authors":"Wenjun Zhao, Kai Meng, Li Sun, Jinhui Ma, Zeguang Jia","doi":"10.1177/01655515231171367","DOIUrl":"https://doi.org/10.1177/01655515231171367","url":null,"abstract":"The rise of social question and answer (Q&A) platforms has changed the model of traditional health-information services. The quality of answers on a Q&A platform is critical to attract users and increase their community engagement. Thus, recognition of the answer was used to measure users’ acceptance of the answer. A theoretical model of the impact of language style on community recognition of health questions was developed. Nearly 1330 answers from a health question from Zhihu were obtained to verify the model. Results showed that personality reliability, assertiveness, argumentation clarity, commitment, and reverse incentive of health information positively affected answer recognition, while argumentation structure negatively affected answer acceptance. Simultaneously, the degree of use of medical terminology has a significant moderating effect on the relationship between answer recognition and assertiveness, argumentation structure, argumentation clarity, and commitment. Introducing Aristotle’s rhetoric theory to language style and answer recognition could potentially develop healthy communities and disseminate health knowledge.","PeriodicalId":54796,"journal":{"name":"Journal of Information Science","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2023-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42230066","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 : 2023-05-06DOI: 10.1177/01655515231171361
Bruno Taborda, Ana Maria de Almeida, José Carlos Dias, Fernando Batista, R. Ribeiro
Sentiment analysis of stock-related tweets is a challenging task, not only due to the specificity of the domain but also because of the short nature of the texts. This work proposes SA-MAIS, a two-step lightweight methodology, specially adapted to perform sentiment analysis in domain-constrained short-text messages. To tackle the issue of domain specificity, based on word frequency, the most relevant words are automatically extracted from the new domain and then manually tagged to update an existing domain-specific sentiment lexicon. The sentiment classification is then performed by combining the updated domain-specific lexicon with VADER sentiment analysis, a well-known and widely used sentiment analysis tool. The proposed method is compared with other well-known and widely used sentiment analysis tools, including transformer-based models, such as BERTweet, Twitter-roBERTa and FinBERT, on a domain-specific corpus of stock market-related tweets comprising 1 million messages. The experimental results show that the proposed approach largely surpasses the performance of the other sentiment analysis tools, reaching an overall accuracy of 72.0%. The achieved results highlight the advantage of using a hybrid method that combines domain-specific lexicons with existing generalist tools for the inference of textual sentiment in domain-specific short-text messages.
{"title":"SA-MAIS: Hybrid automatic sentiment analyser for stock market","authors":"Bruno Taborda, Ana Maria de Almeida, José Carlos Dias, Fernando Batista, R. Ribeiro","doi":"10.1177/01655515231171361","DOIUrl":"https://doi.org/10.1177/01655515231171361","url":null,"abstract":"Sentiment analysis of stock-related tweets is a challenging task, not only due to the specificity of the domain but also because of the short nature of the texts. This work proposes SA-MAIS, a two-step lightweight methodology, specially adapted to perform sentiment analysis in domain-constrained short-text messages. To tackle the issue of domain specificity, based on word frequency, the most relevant words are automatically extracted from the new domain and then manually tagged to update an existing domain-specific sentiment lexicon. The sentiment classification is then performed by combining the updated domain-specific lexicon with VADER sentiment analysis, a well-known and widely used sentiment analysis tool. The proposed method is compared with other well-known and widely used sentiment analysis tools, including transformer-based models, such as BERTweet, Twitter-roBERTa and FinBERT, on a domain-specific corpus of stock market-related tweets comprising 1 million messages. The experimental results show that the proposed approach largely surpasses the performance of the other sentiment analysis tools, reaching an overall accuracy of 72.0%. The achieved results highlight the advantage of using a hybrid method that combines domain-specific lexicons with existing generalist tools for the inference of textual sentiment in domain-specific short-text messages.","PeriodicalId":54796,"journal":{"name":"Journal of Information Science","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2023-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46678955","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：