Proceedings of the XVIII Brazilian Symposium on Information Systems最新文献_第2页

Intelligent Information System for Extracting Knowledge from Pharmaceutical Package Inserts 药品说明书知识提取的智能信息系统

Proceedings of the XVIII Brazilian Symposium on Information Systems Pub Date : 2022-05-16 DOI: 10.1145/3535511.3535558

Cristiano da Silveira Colombo, E. Oliveira

{"title":"Intelligent Information System for Extracting Knowledge from Pharmaceutical Package Inserts","authors":"Cristiano da Silveira Colombo, E. Oliveira","doi":"10.1145/3535511.3535558","DOIUrl":"https://doi.org/10.1145/3535511.3535558","url":null,"abstract":"Pharmaceutical package inserts are a rich source of information about medicines. To guide the patient, health professionals need information about the appropriate medication for an illness. This information can be found in the pharmaceutical package inserts. Extracting information from package inserts manually is a challenging task, especially when information is needed quickly and efficiently. Doubts about adverse reactions or interactions with others drugs are common. Automatically extracting information from package inserts can help health professionals to make decisions about therapies and drug prescriptions. This article describes the creation of an Artificial Intelligence model, using a hybrid approach called CRF+LG, which recognizes named entities of medicines, diseases and people in package inserts. The model was tested on two sets of package inserts: for stomach pain and diabetes treatment. This work was developed under the aegis of Soft Systems Theory. This research has a prescriptive character and its evaluation was carried out through the execution of experiments. The analysis of the results was carried out with a quantitative approach. The experiments showed that the model obtained, of measure F, 82.08% in the recognition of entities related to diseases, 59.14% of medicines and 94.26% of people. The main contribution of the article is the creation of a model that automatically recognizes entities named in pharmaceutical package inserts. This model can integrate an Intelligent Information System to assist health professionals in making decisions about therapies and drug prescription.","PeriodicalId":106528,"journal":{"name":"Proceedings of the XVIII Brazilian Symposium on Information Systems","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123492453","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

How does diversity manifest itself in software ecosystems? 多样性是如何在软件生态系统中表现出来的?

Proceedings of the XVIII Brazilian Symposium on Information Systems Pub Date : 2022-05-16 DOI: 10.1145/3535511.3535521

J. C. S. D. Outão, R. Santos

{"title":"How does diversity manifest itself in software ecosystems?","authors":"J. C. S. D. Outão, R. Santos","doi":"10.1145/3535511.3535521","DOIUrl":"https://doi.org/10.1145/3535511.3535521","url":null,"abstract":"Context: Diversity has been addressed in software ecosystem studies in recent years, aiming at the inclusion and collaboration of different groups within organizations and communities. Its several forms of manifesting have required a better understanding of its effects on the ecosystem. Problem: Since an ecosystem involves the interaction of actors over a common technological platform that supports software solutions or services, the diversity and the relationships between different actors remain a challenge, especially in order to sustain the ecosystem and stimulate its growth. Solution: This study aims to understand how diversity manifests itself in the ecosystem context, based on the existing studies. IS Theory: The research was developed under the aegis of the General Systems Theory, focusing on the relationships between the elements of the system. Method: A systematic mapping study was carried out to identify and characterize how diversity in ecosystems has been discussed, which approaches have been applied and which effects are observed. Results: Based on 13 selected studies, we observed that the most discussed type is demographic diversity and the subtype is gender diversity. It was also noticed that gender diversity increases the productivity of development teams, despite the fact that they are still mostly male. Additionally, an analysis was carried out on how these studies discuss diversity in light of the 15 human, technical and organizational factors of ecosystems. Contribution: The five factors that most affect diversity in ecosystems were identified and actionable approaches were suggested to increase diversity in ecosystems, contributing to the Grand Research Challenge in Information Systems “Information Systems and the Open World Challenges”.","PeriodicalId":106528,"journal":{"name":"Proceedings of the XVIII Brazilian Symposium on Information Systems","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123634308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

How Could Information Systems Support Transparency to Face Corruption? Systematic Mapping of the Literature 资讯系统如何支持透明度以面对贪污?文献的系统映射

Proceedings of the XVIII Brazilian Symposium on Information Systems Pub Date : 2022-05-16 DOI: 10.1145/3535511.3535549

T. Classe, Henrique Prado Sousa, R. Castro

{"title":"How Could Information Systems Support Transparency to Face Corruption? Systematic Mapping of the Literature","authors":"T. Classe, Henrique Prado Sousa, R. Castro","doi":"10.1145/3535511.3535549","DOIUrl":"https://doi.org/10.1145/3535511.3535549","url":null,"abstract":"Context: Corruption is a problem that follows the evolution of humanity, taking root in human society and causing global problems in the form of social inequality, the precariousness of public services, and the exhaustion of democracy. In this scenario, transparency is a necessary action against corruption by providing more precise and complete information so that society can understand and supervise government actions. Public access to those information places Information Systems (ISs) at the center of transparency proposals as tools that can help fight against corruption. Problem: Nevertheless, understanding, designing, and deploying ISs with such a purpose is a challenge because they need distinct features. Solution: Therefore, in this paper, we explored research that helps to understand how ISs could help to face corruption considering transparency aspects, such as features, technologies, and application contexts. Method: We described and used a systematic mapping of the literature (SML) for that. Summary Results: In the search step, we found 124 primary studies but, after evaluation criteria, we accepted only 14 of them as relevant to the research. The results point to potential technologies and features that can make up these ISs, such as data openness and privacy, information traceability, data availability, real-time data, and accountability. Contributions to IS: Thus, this study brings contributions to the SI area by identifying aspects to the project of ISs focused on fighting against corruption by supporting information transparency. In addition, beyond the social relevance of this theme, the research is aligned to the GranDSI-BR 2016-2026.","PeriodicalId":106528,"journal":{"name":"Proceedings of the XVIII Brazilian Symposium on Information Systems","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126637252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Automatic Generation of Large-Scale Assessment Questions 自动生成大规模的评估问题

Proceedings of the XVIII Brazilian Symposium on Information Systems Pub Date : 2022-05-16 DOI: 10.1145/3535511.3535518

Flávio Izo, Jhonatan Leão, Juliana Pinheiro Campos Pirovani, E. Oliveira

{"title":"Automatic Generation of Large-Scale Assessment Questions","authors":"Flávio Izo, Jhonatan Leão, Juliana Pinheiro Campos Pirovani, E. Oliveira","doi":"10.1145/3535511.3535518","DOIUrl":"https://doi.org/10.1145/3535511.3535518","url":null,"abstract":"Assessment is the means used to diagnose learning difficulties. Assessment through questionnaires is one of the ways used to measure the level of content learning by students. Manually elaborating questions is time-consuming and makes the teacher uncomfortable thinking about different questions. Using an automatic question generator allows the teacher to access several questions and apply automatic correction, disseminating assessment results more quickly. If we analyze Massive Open Online Courses (MOOCs), it becomes humanly impossible to correct the large volume of questions manually. We present an institutional tool that recognizes chemical entities from free texts inserted by the teacher and automatically generates questions and their respective answers. We recognized the chemical entities through Local Grammar (LG), and then we elaborated free-text and fill-in-the-blank questions through triplets with spaCy in Python language. To validate the tool, we used two recognized books in Organic Chemistry. Chemistry specialists validated and indicated the level of difficulty of the questions. We generated 64 questions, 33 of which were free-text questions, and 31 were fill-in-the-blank questions. The average of the experts’ assessment indicated that 78,77% (average) and 87,5% (median) of the questions have quality and that most questions have an intermediate difficulty level. This research suggests as main contributions the recognition of named entities in the chemical area and the automatic generation of questions in Portuguese. These tasks can facilitate the human being’s job, reducing the time for generating and correcting questions and reducing institutional costs with such activities.","PeriodicalId":106528,"journal":{"name":"Proceedings of the XVIII Brazilian Symposium on Information Systems","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129332730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Supporting Interorganizational Relationships Management 支持组织间关系管理

Proceedings of the XVIII Brazilian Symposium on Information Systems Pub Date : 2022-05-16 DOI: 10.1145/3535511.3535533

Bruna Diirr, Claudia Cappelli, Douglas Oliveira, Gleison Santos, J. Borges

{"title":"Supporting Interorganizational Relationships Management","authors":"Bruna Diirr, Claudia Cappelli, Douglas Oliveira, Gleison Santos, J. Borges","doi":"10.1145/3535511.3535533","DOIUrl":"https://doi.org/10.1145/3535511.3535533","url":null,"abstract":"Context: Interorganizational relationships have been an option for organizations to remain competitive. They allow resource sharing and collaboration to handle opportunities better. Problem: However, involved organizations may have distinct characteristics, which increase conflicts, influence their alignment, and even lead to interorganizational relationship failure. Solution: To handle such an issue, we outline FIRM, a framework for interorganizational relationships management. IS Theory: A socio-technical theory, which interrelates people-organizations-technology, was adopted for understanding interorganizational relationships and developing FIRM. Method: FIRM was used in a case study of a governmental interorganizational relationship to understand this partnership characteristics/dynamic/issues, besides evaluating FIRM’s potential to systematize interorganizational relationships management. It has a descriptive nature, and we adopted a qualitative approach for results analysis. Summary of Results: Results indicate that FIRM adheres to the depicted partnership reality, helps teams during interorganizational relationships management, and minimizes faced issues since all steps/ associated activities were identified or could be practiced to a greater/lesser degree. Contributions and Impact in the IS area: FIRM benefits interorganizational relationships management since it assists involved parties to become more integrated, prepared to interoperate processes/information, and achieve mutual goals. Moreover, a clear understanding of interorganizational relationships’ social perspective allows proposing technologies that support associated needs, work, and collaboration.","PeriodicalId":106528,"journal":{"name":"Proceedings of the XVIII Brazilian Symposium on Information Systems","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114655201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Understanding Interaction and Organizational Issues in Radiology Information Systems: a Qualitative Study with Health Professionals 理解放射学信息系统中的相互作用和组织问题:与卫生专业人员的定性研究

Proceedings of the XVIII Brazilian Symposium on Information Systems Pub Date : 2022-05-16 DOI: 10.1145/3535511.3535557

Fabio Aparecido Candido Aparecido da Silva, M. Pereira, A. P. Freire

{"title":"Understanding Interaction and Organizational Issues in Radiology Information Systems: a Qualitative Study with Health Professionals","authors":"Fabio Aparecido Candido Aparecido da Silva, M. Pereira, A. P. Freire","doi":"10.1145/3535511.3535557","DOIUrl":"https://doi.org/10.1145/3535511.3535557","url":null,"abstract":"Context. Interaction with information systems such as PACS and RIS/HIS have been increasingly important in medical practice in hospitals and clinics and are essential for health professionals to perform their activities. Problem. These systems can present usability problems, compromising the efficiency of the process, generating incorrect diagnoses, delays in service and results. Proposal. The aim of this study was to investigate interaction and organizational issues with the use of radiology information systems by health professionals. Theoretical Approach. This qualitative study concerns the work routine of radiology professionals, cognitive learning, interaction and usability problems with systems and other radiology software. Method. The paper presents an exploratory study with thematic analysis of semi-structured interviews with eleven radiology professionals recruited via social networks and e-mails. The interview guide includes the process, responsibilities and factors that interfere in the routine of radiology professionals. Results. Thematic analysis revealed 5 themes that indicate the factors that interfere in the user’s routine and in the radiological context, namely: System characteristics affect user usability; Process situations affect user task characteristics; User’s behavior in relation to his routine; User experience and knowledge; Users deal with system failures and data loss risks. Contribution and Impact on IS. The results show that the users’ routine and interaction with radiology systems are conditioned to hospital or clinical processes, limiting users. The analysis of this study contributes to highlight usability aspects and business processes that can be improved in (clinical contexts) for a better effectiveness of radiological information systems.","PeriodicalId":106528,"journal":{"name":"Proceedings of the XVIII Brazilian Symposium on Information Systems","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123164486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

An Overview on the Use of Adversarial Learning Strategies to Ensure Fairness in Machine Learning Models 在机器学习模型中使用对抗性学习策略以确保公平性的概述

Proceedings of the XVIII Brazilian Symposium on Information Systems Pub Date : 2022-05-16 DOI: 10.1145/3535511.3535517

Luiz Fernando F. P. de Lima, D. R. D. Ricarte, C. Siebra

{"title":"An Overview on the Use of Adversarial Learning Strategies to Ensure Fairness in Machine Learning Models","authors":"Luiz Fernando F. P. de Lima, D. R. D. Ricarte, C. Siebra","doi":"10.1145/3535511.3535517","DOIUrl":"https://doi.org/10.1145/3535511.3535517","url":null,"abstract":"Context: The information age brought wide data availability, which allowed technological advances, especially when looking at machine learning (ML) algorithms that have achieved significant results for the most diverse tasks. Thus, information systems are now implementing and incorporating these algorithms, including in critical areas. Problem: Given this widespread use and already observed examples of misuse of its decisions, it is essential to consider the harm and social impacts that ML models can bring for society, for example, biased and discriminatory decisions coming from biased data or programmers. Solution: This article provides an overview of an eminent area of study on the use of adversarial learning to encode fairness constraints in ML models. IS Theory: This work is related to socio-technical theory since we consider one of the so-called socio-algorithmic problems, algorithmic discrimination. We consider a specific set of approaches to encoding fair behaviors. Method: We selected and analyzed the literature works on the use of adversarial learning for encoding fairness, aiming to answer defined research questions. Summary of Results: As main results, this work presents answers to the following research questions: What is the type of their approach? What fairness constraints did they encode into their models? What evaluation metrics did they use to assess their proposals? What datasets did they use? Contributions and Impact in the IS area: We expect to assist future research in the fairness area. Thus the article’s main contribution is to provide a reference for the community, summarizing the main topics about the adversarial learning approaches for achieving fairness.","PeriodicalId":106528,"journal":{"name":"Proceedings of the XVIII Brazilian Symposium on Information Systems","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124645213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Applications of Artificial Intelligence for Auditing and Classification of Incongruent Descriptions in Public Procurement 人工智能在公共采购不一致描述审计与分类中的应用

Proceedings of the XVIII Brazilian Symposium on Information Systems Pub Date : 2022-05-16 DOI: 10.1145/3535511.3535551

Wesckley Faria Gomes, Methanias Colaço

{"title":"Applications of Artificial Intelligence for Auditing and Classification of Incongruent Descriptions in Public Procurement","authors":"Wesckley Faria Gomes, Methanias Colaço","doi":"10.1145/3535511.3535551","DOIUrl":"https://doi.org/10.1145/3535511.3535551","url":null,"abstract":"Context: Despite the advancement of technology, many services and information systems, especially in the public sector, still use unstructured natural language descriptions of products, services, or events, making their classification and analysis difficult. For efficient audits, it is necessary to classify and automatically totalize invoices issued for the purchase of products, considering their unique identification codes. Problem: The codes are not always registered correctly by the suppliers. Furthermore, if the product description is considered an alternative to the code, as aforementioned, this is not a uniform field, having free and variable writing. Solution: This work aimed to identify and characterize the approaches, techniques and intelligent algorithms used to classify incongruous textual descriptions present in the invoices issued. IS theory: General systems theory; Competitive strategy (Porter); Knowledge-based theory of the firm. Method: A systematic mapping was conducted to find the primary studies in the literature and collect evidence for directing future research. Summary of Results: 225 articles were identified, with Scopus and Web of Science being the bases with the most articles. Only 15 articles passed the inclusion and exclusion criteria. Among the approaches used, supervised machine learning stands out, present in 60% of the works. The most widely used techniques were Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), present in 40% of the articles. Contributions and Impacts in the IS area: The research showed that the use of artificial intelligence techniques helped to mitigate the problem of classification and analysis of invoices with incongruous codes and descriptions, which can help in the audit process, investigation, and fight against corruption. Finally, trends and gaps to be explored were also presented.","PeriodicalId":106528,"journal":{"name":"Proceedings of the XVIII Brazilian Symposium on Information Systems","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129616262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Investigating Information Security in Systems-of-Systems 研究系统的信息安全

Proceedings of the XVIII Brazilian Symposium on Information Systems Pub Date : 2022-05-16 DOI: 10.1145/3535511.3535523

R. Dias, Rodrigo Oliveira Zacarias, Jorge Luis de Lima Varella, R. Santos

{"title":"Investigating Information Security in Systems-of-Systems","authors":"R. Dias, Rodrigo Oliveira Zacarias, Jorge Luis de Lima Varella, R. Santos","doi":"10.1145/3535511.3535523","DOIUrl":"https://doi.org/10.1145/3535511.3535523","url":null,"abstract":"Context: Changes in society have made information systems more complex. This also happens to a category of systems defined as system-of-systems (SoS) and system-of-information systems (SoIS). Problem: Although SoS offers benefits to organizations, the difficulty of IT managers in dealing with information security in these systems can leave them vulnerable to threats and impacts caused by cyber-attacks. Solution: This study presents mechanisms and technologies that should be implemented to ensure that communication between systems is treated from the perspective of information security. IS theory: This research is based on the General Systems Theory that allows to understand SoS as a type of complex system. With the increase in tasks complexity, constituent systems collaborate and offer functionalities that could not be achieved by them in an isolated form. Method: A systematic mapping study (SMS) was carried out to identify how information security technologies are used in the context of SoS. Moreover, a survey research was conducted to analyze information security aspects in order to evaluate the results obtained in the SMS with respect to their applicability in industry. Summary of Results: 18 studies were reviewed in the SMS and 32 experts participated in the survey. Both studies show that stakeholders need to understand vulnerabilities, exposure, and the contribution technology makes to prevent cyberattacks and mitigate SoS risks. Contributions and Impact in the IS area: This work presents an overview of information security in SoS, highlighting related technologies so that stakeholders can reflect on cyber threats in decision-making processes in organizations, exploring the grand research challenge in IS “Smart Systems-of-Information Systems: Foundations and an Assessment Model for Research Development”.","PeriodicalId":106528,"journal":{"name":"Proceedings of the XVIII Brazilian Symposium on Information Systems","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114608605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Predicting IMDb Rating of TV Series with Deep Learning: The Case of Arrow 用深度学习预测电视剧的IMDb评分:以《绿箭侠》为例

Proceedings of the XVIII Brazilian Symposium on Information Systems Pub Date : 2022-05-16 DOI: 10.1145/3535511.3535520

Anna Luiza Gomes, Getúlio Vianna, Tatiana Escovedo, Marcos Kalinowski

{"title":"Predicting IMDb Rating of TV Series with Deep Learning: The Case of Arrow","authors":"Anna Luiza Gomes, Getúlio Vianna, Tatiana Escovedo, Marcos Kalinowski","doi":"10.1145/3535511.3535520","DOIUrl":"https://doi.org/10.1145/3535511.3535520","url":null,"abstract":"Context: The number of TV series offered nowadays is very high. Due to its large amount, many series are canceled due to a lack of originality that generates a low audience. Problem: Having a decision support system that can show why some shows are a huge success or not would facilitate the choices of renewing or starting a show. Solution: We studied the case of the series Arrow broadcasted by CW Network and used descriptive and predictive modeling techniques to predict the IMDb rating. We assumed that the theme of the episode would affect its evaluation by users, so the dataset is composed only by the director of the episode, the number of reviews that episode got, the percentual of each theme extracted by the Latent Dirichlet Allocation (LDA) model of an episode, the number of viewers from Wikipedia and the rating from IMDb. The LDA model is a generative probabilistic model of a collection of documents made up of words. IS Theory: This study was developed under the aegis of Computational Learning Theory, which aims to understand the fundamental principles of learning and contribute to designing better-automated learning methods applied to the entertainment business. Method: In this prescriptive research, the case study method was used, and its results were analyzed using a quantitative approach. Summary of Results: With the features of each episode, the model that performed the best to predict the rating was Catboost due to a similar mean squared error of the KNN model but a better standard deviation during the test phase. It was possible to predict IMDb ratings with an acceptable root mean squared error of 0.55. Contributions and Impact in the IS area: The results show that deep learning techniques can be applied to support decisions in the entertainment field, allowing facilitating the decisions of renewing or starting a show. The rationale for building the model is detailed throughout the paper and can be replicated for other contexts.","PeriodicalId":106528,"journal":{"name":"Proceedings of the XVIII Brazilian Symposium on Information Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125906959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0