Leveraging Social Media Metrics in Improving Social Media Performances through Organic Reach: A Data Mining Approach

AbstractThis paper identified the relevance of several publication’s characteristics of each publication in reaching more people through organic strategy using Support Vector Machines. Before finding the relevance of several inputs, 10 potential models were examined. Based on the results of 10 models examination, we found that Comments, Likes and Shares have smallest error. However, those variables represent the customer engagements, instead of reaching more people. In the other side, Lifetime total organic reach is the best model compares to other models, therefore lifetime total organic reach was selected as a model. Furthermore, page total likes were found as the most relevance input in reaching more people through organic reach. The next most relevance inputs were followed by Type, month, day and hour of publication. Eventually, we come up with a managerial implication on how to publish a post in order to reach more people through organic reach.

Download Full-text

Credit scoring with a data mining approach based on support vector machines

Expert Systems with Applications ◽

10.1016/j.eswa.2006.07.007 ◽

2007 ◽

Vol 33 (4) ◽

pp. 847-856 ◽

Cited By ~ 397

Author(s):

Cheng-Lung Huang ◽

Mu-Chen Chen ◽

Chieh-Jen Wang

Keyword(s):

Data Mining ◽

Support Vector Machines ◽

Credit Scoring ◽

Support Vector ◽

Data Mining Approach ◽

Vector Machines

Download Full-text

Proposta de metodologia para a criação de etiqueta de classificação – estudo de caso: desempenho escolar

Gestão & Produção ◽

10.1590/0104-530x810-13 ◽

2016 ◽

Vol 23 (1) ◽

pp. 177-191

Author(s):

Anderson Roges Teixeira Góes ◽

Maria Teresinha Arns Steiner

Keyword(s):

Data Mining ◽

Support Vector Machines ◽

Knowledge Discovery ◽

Knowledge Discovery In Databases ◽

Support Vector ◽

Vector Machines

Resumo A qualidade na educação tem sido objeto de muita discussão, seja nas escolas e entre seus gestores, seja na mídia ou na literatura. No entanto, uma análise mais profunda na literatura parece não indicar técnicas que explorem bancos de dados com a finalidade de obter classificações para o desempenho escolar, nem tampouco há um consenso sobre o que seja “qualidade educacional”. Diante deste contexto, neste artigo, é proposta uma metodologia que se enquadra no processo KDD (Knowledge Discovery in Databases, ou seja, Descoberta de Conhecimento em Bases de Dados) para a classificação do desempenho de instituições de ensino, de forma comparativa, com base nas notas obtidas na Prova Brasil, um dos itens integrantes do Índice de Desenvolvimento da Educação Básica (IDEB) no Brasil. Para ilustrar a metodologia, esta foi aplicada às escolas públicas municipais de Araucária, PR, região metropolitana de Curitiba, PR, num total de 17, que, por ocasião da pesquisa, ofertavam Ensino Fundamental, considerando as notas obtidas pela totalidade dos alunos dos anos iniciais (1º. ao 5º. ano do ensino fundamental) e dos anos finais (6º. ao 9º. ano do ensino fundamental). Na etapa de Data Mining, principal etapa do processo KDD, foram utilizadas três técnicas de forma comparativa para o Reconhecimento de Padrões: Redes Neurais Artificiais; Support Vector Machines; e Algoritmos Genéticos. Essas técnicas apresentaram resultados satisfatórios na classificação das escolas, representados por meio de uma “Etiqueta de Classificação do Desempenho”. Por meio desta etiqueta, os gestores educacionais poderão ter melhor base para definir as medidas a serem adotadas junto a cada escola, podendo definir mais claramente as metas a serem cumpridas.

Download Full-text

Data Mining with Parallel Support Vector Machines for Classification

Advances in Information Systems - Lecture Notes in Computer Science ◽

10.1007/11890393_21 ◽

2006 ◽

pp. 197-206 ◽

Cited By ~ 4

Author(s):

Tatjana Eitrich ◽

Bruno Lang

Keyword(s):

Data Mining ◽

Support Vector Machines ◽

Support Vector ◽

Vector Machines

Download Full-text

Prediction of course completion by students of a university in Brazil

Psico-USF ◽

10.1590/1413-82712018230303 ◽

2018 ◽

Vol 23 (3) ◽

pp. 425-436

Author(s):

Alessandra Turini Bolsoni-Silva ◽

Rommel Melgaço Barbosa ◽

Alessandra Salina Brandão ◽

Sonia Regina Loureiro

Keyword(s):

Data Mining ◽

Academic Performance ◽

Support Vector Machines ◽

Young People ◽

University Students ◽

Course Completion ◽

Simple Approach ◽

Support Vector ◽

Reliability Sensitivity ◽

Vector Machines

Abstract The conclusion of the undergraduate course by university students in the time predicted by the curriculum is desirable for young people and for society. The aim was to verify the reliability, sensitivity and specificity of a broad set of predictors for academic performance of university students, who completed the undergraduate course within the time predicted by the curricula, through data mining methodology, provided by the Support Vector Machines algorithm. A simple approach is proposed for the prediction of course completion by students in a university in Brazil. The dataset has 170 students who finished the course and 117 who did not finish. With the proposed methodology, it was possible to predict the course completion by students with an accuracy of 79.5% when using the 19 original variables. An accuracy of 75% was found using only 05 variables: Course, year of the course, gender, initial and final academic performance.

Download Full-text