Question 15 [4 points] What is NOT one of the difficulties of mining association rules from large databases? 0 The cardinality of item-sets in most situations is extremely large, and the volume of transactions is very high as vvell. Some operational databases in retailing and communication industries collect tens of millions of transactions per day. 0 Transactions show variability in such factors as geographic location and seasons, making sampling difficult. 0 Quality of data is variable; significant problems exist with missing, erroneous, conflicting, as well as redundant data in many industries 0 All of these ARE correct factors that may complicate mining association rules from large databases. Question 9 (4 points) Given a document containing only the following terms with given frequencies: Apple 102, Banana 2 x 102, and Cherry 3 x 102. Which of the following choices provides the normalized term frequency. Otf(Apple)= 1/6, tf(Banana) = 1/3, tf(Cherry)=1/2 Otf(Apple)= log(10), tf(Banana) = 2log(10), tf(Cherry)= 3log(10) tf(Apple)= 1, tf(Banana) = 2, tf(Cherry)=3 Otf(Apple)= log(1/6), tf(Banana) = log(1/3), tf(Cherry)=log(1/2)Question 11 (4 points) Suppose we would like to rank a set of documents according to a particular query, and the content of all is a list of arithmetic expressions. To achieve a reliable and interpretable solution, which Information Retrieval model should be employed? O a) Boolean Model O b) Vector Space Model O c) Semantic Model O d) Any of these, as all of them will give the same result