کاربرد داده کاوی آموزشی جهت شناسایی عوامل موثر بر افت تحصیلی دانش آموزان

اﺳﺘﺨﺮاج داﻧﺶ ﯾﮑﯽ از ﻣﻬﻤﺘﺮﯾﻦ ﻣﺴﺎﺋﻞ دادهﮐﺎوی ﻣﯽﺑﺎﺷﺪ. ﻗﻮاﻧﯿﻨﯽ ﮐﻪ ﺑﻪﺻﻮرت اﮔﺮ - آﻧﮕﺎه ﻣﻄﺮحﻣﯽﮔﺮدﻧﺪ اﯾﻦ ﺗﻮاﻧﺎﯾﯽ را دارﻧﺪ ﮐﻪ ﺑﻪ ﺻﻮرت اﻋﺪاد ﺣﻘﯿﻘﯽ در ﻫﺮ ﺟﺰء ﺑﻪ ﺻﻮرت ﺗﻤﺎم ﻣﻘﺎدﯾﺮی ﮐﻪ در ﻣﺠﻤﻮﻋﻪداده ﻣﯽﺗﻮاﻧﺪ وﺟﻮدداﺷﺘﻪﺑﺎﺷﺪ، ﻗﺮارﮔﯿﺮﻧﺪ. روش ﭘﯿﺸﻨﻬﺎدی در اﯾﻦ ﻣﻘﺎﻟﻪ اﺳﺘﻔﺎده از اﻟﮕﻮرﯾﺘﻢﻫﺎی درﺧﺖ ﺗﺼﻤﯿﻢ و ﺧﻮﺷﻪﺑﻨﺪی و ﻗﻮاﻧﯿﻦ اﻧﺠﻤﻨﯽ ﺑﺮای اﺳﺘﺨﺮاج ﻗﻮاﻧﯿﻦ ﻣﯽﺑﺎﺷﺪ. در روش ﭘﯿﺸﻨﻬﺎدی اﺳﺘﺨﺮاج ﻗﻮاﻧﯿﻦ را ﺑﻪ ﺻﻮرت ﯾﮏ ﻣﺴﺌﻠﻪ ﺑﻬﯿﻨﻪﺳﺎزی در آورده و ﻫﺪف ﺑﻪدﺳﺖآوردن ﻗﺎﻧﻮﻧﯽ ﺑﺎ اﻃﻤﯿﻨﺎن ﺑﺎﻻ، ﻋﻤﻮﻣﯿﺖ و ﻗﺎﺑﻠﯿﺖ درک ﺑﺎﻻ ﻣﯽﺑﺎﺷﺪ. اﻟﮕﻮرﯾﺘﻢ ﭘﯿﺸﻨﻬﺎدی ﺑﺮای اﺳﺘﺨﺮاج ﻗﻮاﻧﯿﻦ ازﻣﺠﻤﻮﻋﻪ داده اﻓﺖ ﺗﺤﺼﯿﻠﯽ از اﻃﻼﻋﺎت ﻓﺮدی 256 داﻧﺶآﻣﻮزان ﻫﻨﺮﺳﺘﺎن ﻫﺎ در زﻧﺠﺎن ﺟﻤﻊآوری و آزﻣﺎﯾﺶﺷﺪ. ﻧﺘﺎﯾﺞ ﻧﺸﺎنداد ﮐﻪ اﻟﮕﻮرﯾﺘﻢ j48 در درﺧﺖ ﺗﺼﻤﯿﻢ ﺑﺎ دﻗﺖ 0,95 ﺑﺮای ﻣﺠﻤﻮﻋﻪ داده اﻓﺖ ﺗﺤﺼﯿﻠﯽ و ﺧﻮﺷﻪﺑﻨﺪی دادهﻫﺎ ﺑﺎ اﻟﮕﻮرﯾﺘﻢ k-main ﺑﺎ ﺿﺮﯾﺐ اﻃﻤﯿﻨﺎن 0,95 و ﺑﻪدﺳﺖآوردن ﻗﻮاﻧﯿﻦ ﺑﺎ ﺿﺮﯾﺐ اﻃﻤﯿﻨﺎن ﺑﺎﻻ ﺑﺎ اﺳﺘﻔﺎده از ﻗﻮاﻧﯿﻦ اﻧﺠﻤﻨﯽ ﮐﻪ از اﻟﮕﻮرﯾﺘﻢ apriori ﺑﺮای ﻣﺠﻤﻮﻋﻪ دادهﻫﺎ اﺟﺮا و ﺗﻮﻟﯿﺪ ﺷﺪ. از ﻧﺘﺎﯾﺞ ﺑﻪدﺳﺖآﻣﺪه از اﯾﻦ ﺗﺤﻘﯿﻖ ﻣﯽﺗﻮان ﺑﺮای ﭘﯿﺸﮕﯿﺮی از اﻓﺖ ﺗﺤﺼﯿﻠﯽ داﻧﺶآﻣﻮزان و ﺑﻬﺒﻮد ﮐﯿﻔﯿﺖ ارﺗﺒﺎط ﻣﺴﺌﻮﻟﯿﻦ و واﻟﺪﯾﻦ ﺑﺎ داﻧﺶآﻣﻮزان و آﻣﻮزش ﻫﺮﭼﻪ ﺑﻬﺘﺮ آﻧﺎن اﺳﺘﻔﺎدهﮐﺮد.

use data mining to identify factors affecting students’ academic failure

knowledge extraction is one of the most significant problems of data mining. the principles raised in if-then format can be turned into real numbers in each section- as values which could be included in dataset. the suggested method in the present dissertation is application of decision tree algorithms, clustering and forum rules for extraction of final rules. in the suggested method, extraction of rules is defined as an optimization problem and objective was obtaining a rule of high confidence, generalization and understandability. the suggested algorithm for extraction of rules was obtained from and tested based on a dataset of educational failure of 256 art school students living in zanjan. the results suggested that the j48 algorithm in decision tree and accuracy of 0.95 is the choice for the dataset of educational failure. data clustering was done by k-main algorithm with confidence coefficient of 0.95. after all, obtaining rules of high confidence coefficient was done based on forum rules from apriori algorithm for the whole datasets. the results of present study could be used for inhibition of educational failure of students, improved quality of relationship of parents and authorities with students and enhancing the education they receive.