Open AccessSieve Diagram For Data Exploration of Instagram Usage Habit Obtained From Indonesia Questioner’s Sample
Author(s) -
Reko Syarif Hidayatullah,
Wahyu Nur Cholifah,
Erlin Windia Ambarsari,
Nunu Kustian,
Siti Julaeha
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1783/1/012028
Subject(s) - respondent , sieve (category theory) , habit , diagram , tree diagram , categorical variable , sample (material) , decision tree , computer science , categorization , statistics , mathematics , data mining , psychology , artificial intelligence , social psychology , combinatorics , bayesian probability , chemistry , posterior probability , chromatography , political science , law
Exploration data using a scatter plot made it more accessible when the datasets correlated. However, the case of Instagram Usage Habit in the previous study was hard to follow. The problem was that many datasets were not specific. Therefore, it difficult to classification for a Decision Tree. The other option of exploration data used the sieve diagram. The sieve diagram summarizes the relationship between the categorical variables using frequencies—the purpose of this study to understand the data and found out what wrong in the datasets. Based on the result of the sieve diagram in the study, the main problem found out in the age of the respondent on attributes. We deduce that several attributes had not characteristic unique for the habit of using Instagram because the attributes based on age have a similar pattern. We suggest that the questions for respondents need to be improved, such as Tiered questions. Therefore, The classification of decision trees would become more precise in the subsequent studies.