Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021)最新文献

How concept drift can impair the classification of fake news 概念漂移如何影响假新闻的分类

Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021) Pub Date : 2021-10-04 DOI: 10.5753/kdmile.2021.17469

R. M. Silva, Tiago A. Almeida

{"title":"How concept drift can impair the classification of fake news","authors":"R. M. Silva, Tiago A. Almeida","doi":"10.5753/kdmile.2021.17469","DOIUrl":"https://doi.org/10.5753/kdmile.2021.17469","url":null,"abstract":"Fake news is a serious problem that can influence political choices, harm people's physical and mental health, promote treatments without scientific evidence, and even incite violence. Machine learning methods are one of the leading solutions that have been studied for filtering fake news automatically. However, most studies do not consider the dynamic nature of news, creating static models and evaluating them offline through the traditional holdout or cross-validation. These studies naively assume that news characteristics do not change over time and, therefore, the performance of offline models is preserved as time goes on. In this study, we show how concept drift can impair the classification of fake news. We aim to verify whether the conclusions obtained in studies that disregarded the dynamic nature of the news are sustained. We analyzed how the performance of methods trained in an offline fashion is affected by the news update over time, including concept drift due to impacting events like the Covid-19 pandemic and the United States presidential election. The results showed that the performance of offline models is over-optimistic. Incremental learning methods should be preferred because they can adapt to changes in textual patterns over time.","PeriodicalId":391667,"journal":{"name":"Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128358048","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: 4

Survival Prediction for Oral Cancer Patients: A Machine Learning Approach 口腔癌患者生存预测:机器学习方法

Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021) Pub Date : 2021-10-04 DOI: 10.5753/kdmile.2021.17466

Murilo Cruz Lopes, Marília de Matos Amorim, V. S. Freitas, R. Calumby

{"title":"Survival Prediction for Oral Cancer Patients: A Machine Learning Approach","authors":"Murilo Cruz Lopes, Marília de Matos Amorim, V. S. Freitas, R. Calumby","doi":"10.5753/kdmile.2021.17466","DOIUrl":"https://doi.org/10.5753/kdmile.2021.17466","url":null,"abstract":"There is a high incidence of oral cancer in Brazil, with 150,000 new cases estimated for 2020-2022. In most cases, it is diagnosed at an advanced stage and are related to many risk factors. The Registro Hospitalar de Câncer (RHC), managed by Instituto Nacional de Câncer (INCA), is a nation-wide database that integrates cancer registers from several hospitals in Brazil. RHC is mostly an administrative database but also include clinical, socioeconomic and hospitalization data for each patient with a cancer diagnostic in the country. For these patients, prognostication is always a difficult task a demand multi-dimensional analysis. Therefore, exploiting large-scale data and machine intelligence approaches emerge as promising tool for computer-aided decision support on death risk estimation. Given the importance of this context, some works have reported high prognostication effectiveness, however with extremely limited data collections, relying on weak validation protocols or simple robustness analysis. Hence, this work describes a detailed workflow and experimental analysis for oral cancer patient survival prediction considering careful data curation and strict validation procedures. By exploiting multiple machine learning algorithms and optimization techniques the proposed approach allowed promising survival prediction effectiveness with F1 and AuC-ROC over 0.78 and 0.80, respectively. Moreover, a detailed analysis have shown that the minimization of different types of prediction errors were achieved by different models, which highlights the importance of the rigour in this kind of validation.","PeriodicalId":391667,"journal":{"name":"Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129311161","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

Credit scoring development in the light of the new Brazilian General Data Protection Law 根据新的巴西通用数据保护法，信用评分的发展

Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021) Pub Date : 2021-10-04 DOI: 10.5753/kdmile.2021.17462

Robinson A. A. de Oliveira-Junior

引用次数: 0

Analysis and Prediction of Childhood Pneumonia Deaths using Machine Learning Algorithms 使用机器学习算法分析和预测儿童肺炎死亡

Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021) Pub Date : 2021-10-04 DOI: 10.5753/kdmile.2021.17456

F. Soares, Efrem E. O. Lousada, T. Silveira, R. Mini, Luis E. Zárate, H. Freitas

{"title":"Analysis and Prediction of Childhood Pneumonia Deaths using Machine Learning Algorithms","authors":"F. Soares, Efrem E. O. Lousada, T. Silveira, R. Mini, Luis E. Zárate, H. Freitas","doi":"10.5753/kdmile.2021.17456","DOIUrl":"https://doi.org/10.5753/kdmile.2021.17456","url":null,"abstract":"Acute Respiratory Tract Infections are among the leading causes of child mortality worldwide. Specifically, community-acquired pneumonia has different causes, such as: passive smoking, air pollution, poor hygiene, cardiac insufficiency, oropharyngeal colonization, nutritional deficiency, immunosuppression, and environmental, economic and social factors. Due to the variation of these causes, knowledge discovery in this area of health has been a great challenge for researchers. Thus, this paper presents the steps for the construction of a database and evaluation results applied to the analysis and prediction of potential deaths caused by childhood pneumonia using the Pictorea method. For this, the Random Forest and Artificial Neural Network algorithms were used, and after comparison, the Neural Network algorithm showed higher accuracy by up to 87.57%. This algorithm was used to analyze and predict the number of deaths from pneumonia in children up to 5 years old, and the results were presented using Root Mean Square Error and scatter plots. A domain specialist validated the results and defined that the pattern found is relevant for future studies in the medical field, helping to analyze the behavior of countries and predict future scenarios.","PeriodicalId":391667,"journal":{"name":"Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124329279","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

Enriching datasets for sentiment analysis in tweets with instance selection 通过实例选择丰富推文情感分析的数据集

Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021) Pub Date : 2021-10-04 DOI: 10.5753/kdmile.2021.17463

Eliseu Guimarães, Daniela Vianna, A. Paes, A. Plastino

引用次数: 0

Text Classification in Law Area: a Systematic Review 法律领域的文本分类:系统回顾

Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021) Pub Date : 2021-10-04 DOI: 10.5753/kdmile.2021.17458

V. S. Martins, C. D. Silva

引用次数: 2

Pro/Anti-vaxxers in Brazil: a temporal analysis of COVID vaccination stance in Twitter 巴西的支持/反对疫苗接种者:Twitter上对COVID疫苗接种立场的时间分析

Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021) Pub Date : 2021-10-04 DOI: 10.5753/kdmile.2021.17467

Andre Mediote de Sousa, Karin Becker

引用次数: 5

Topic Modeling of Committee Discussions in the Brazilian Chamber of Deputies 巴西众议院委员会讨论的主题建模

Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021) Pub Date : 2021-10-04 DOI: 10.5753/kdmile.2021.17460

M. A. dos Santos, N. Andrade, F. Morais

引用次数: 0

Commodities trend link prediction on heterogeneous information networks 异构信息网络下的商品趋势链接预测

Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021) Pub Date : 2021-10-04 DOI: 10.5753/kdmile.2021.17464

P. D. do Carmo, I. J. Reis Filho, R. Marcacini

{"title":"Commodities trend link prediction on heterogeneous information networks","authors":"P. D. do Carmo, I. J. Reis Filho, R. Marcacini","doi":"10.5753/kdmile.2021.17464","DOIUrl":"https://doi.org/10.5753/kdmile.2021.17464","url":null,"abstract":"Events can be defined as an action or a series of actions that have a determined theme, time, and place. Event analysis tasks for knowledge extraction from news and social media have been explored in recent years. However, there are still few studies that aim to enrich predictive models using event data. In particular, agribusiness events have multiple components to be considered for a successful prediction model. For example, price trend predictions for commodities can be performed through time series analysis of prices, but we can also consider events that represent knowledge about external factors during the training step of predictive models. In this paper, we present a method for integrating events into trend prediction tasks. First, we propose to model events and time-series information through heterogeneous information networks (HIN) that allow multiple components to be directly modeled through multi-type nodes and edges. Second, we learn features from HIN through network embedding methods, i.e., network nodes are mapped to a dense vector of features. In particular, we propose a network embedding method that propagates the semantic of the pre-trained neural language models to a heterogeneous information network and evaluates its performance in a trend link prediction. We show that the use of our proposed model language-based embedding propagation is competitive with state-of-art network embeddings algorithms. Moreover, our proposal performs network embedding incrementally, thereby allowing new events to be inserted in the same semantic space without rebuilding the entire network embedding.","PeriodicalId":391667,"journal":{"name":"Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127788257","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

A sketch for the KS test for Big Data 大数据的KS测试草图

Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021) Pub Date : 2021-10-04 DOI: 10.5753/kdmile.2021.17455

Thalis D. Galeno, João Gama, D. O. Cardoso

引用次数: 1