{"id":2960,"date":"2019-08-15T23:42:32","date_gmt":"2019-08-16T05:12:32","guid":{"rendered":"https:\/\/www.questionbang.com\/blog\/?p=2960"},"modified":"2019-08-15T23:42:32","modified_gmt":"2019-08-16T05:12:32","slug":"when-mock-set-plus-insists-for-a-trustspot-review","status":"publish","type":"post","link":"https:\/\/www.questionbang.com\/blog\/2019\/08\/15\/when-mock-set-plus-insists-for-a-trustspot-review\/","title":{"rendered":"When mock-set-plus Insists For A TrustSpot Review?"},"content":{"rendered":"

 <\/p>\n

Questionbang\u00a0mock-set-plus<\/a> is a premier assessment platform for various competitive exams including NEET<\/a>, JEE<\/a> and Bank exams<\/a>. The application offers a feature to provide feedback once a user attempts a free mock exam. These reviews are captured and recorded through TrustSpot<\/a>.<\/p>\n

As a part of internship, I wanted to use machine learning (ML) to decide whether a user is a potential reviewer and be insisted for a feedback.<\/p>\n

 <\/p>\n

Importance of user reviews<\/h3>\n

The success of any application depends on how it meets user expectations. It is vital for any application to constantly evolve to address changing user requirements and expectations. This can be possible only by gathering regular reviews from the user community.<\/p>\n

Every topic in mock-set-plus has a free mock exam. These are of short duration. Most users who visit\u00a0mock-set-plus<\/a> attempt free papers to have a quick overview of online mock exams. They are asked to give a feedback and a star rating immediately after completing the exam session.<\/p>\n

\"\"<\/a><\/p>\n

Figure 1. mock-set-plus asking for TrustSpot reviews.<\/p>\n

Not many users give feedback or rating, they simply skip over to the next stage for reviewing results. Now, whether a user be reminded to give feedback? It is not going to be a good user experience, if an application regularly asks users for reviews or other feedback. So, we need to be careful while seeking second time for the review. To make this process restrained, we wanted to classify users based on whether they are potential reviewers or not.<\/code><\/p>\n

 <\/p>\n

Scenario 1<\/strong><\/p>\n

A user who hardly attempted questions, ends a session without giving any feedback.<\/p>\n

 <\/p>\n

Scenario 2<\/strong><\/p>\n

A user who does extremely well with an exam, but skips over without giving feedback.<\/p>\n

 <\/p>\n

In scenario (1), let us assume, the user did not like any of the questions or the user felt the mock exam is not worthy of attempting. But, a feedback on why the application has been disliked, can be a valuable input. We should insist such a user for a feedback.<\/p>\n

In scenario (2), the user might have found\u00a0the questions<\/span>\u00a0to be obvious or ordinary. The application would really benefit by having this feedback.<\/p>\n

In short, every user can be a source of valuable feedback. The only concern now is whether a user be insisted to give a feedback?<\/p>\n

Let us use historical data from TrustSpot<\/a> reviews to decide whether a user is a potential reviewer.<\/p>\n

 <\/p>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
User<\/th>\nQ attempted
\n(Q)<\/th>\n		Time spent
\n(T) in minutes<\/th>\n		Score
\n(S)<\/th>\n		Reviewed or not<\/th>\n<\/tr>\n<\/thead>\n
\u00a0Sonal S<\/td>\n\u00a0\"\frac{5}{5}\"<\/td>\n\u00a0\"\frac{3}{5}\"<\/span><\/td>\n\u00a0\"\frac{1}{5}\"<\/span><\/td>\n\u00a0\u00a0Yes<\/td>\n<\/tr>\n
krishna<\/td>\n\u00a0\"\frac{0}{5}\"<\/span><\/td>\n\u00a0\"\frac{1}{5}\"<\/span><\/td>\n\u00a0\"\frac{0}{5}\"<\/span><\/td>\n\u00a0 No<\/td>\n<\/tr>\n
Meghana R<\/td>\n\u00a0\"\frac{5}{5}\"<\/span><\/td>\n\u00a0\"\frac{3}{5}\"<\/span><\/td>\n\u00a0\"\frac{1}{5}\"<\/span><\/td>\n\u00a0\u00a0Yes<\/td>\n<\/tr>\n
Pooja Thathera<\/td>\n\u00a0\"\frac{5}{5}\"<\/span><\/td>\n\u00a0\"\frac{2}{5}\"<\/span><\/td>\n\u00a0\"\frac{3}{5}\"<\/span><\/td>\n\u00a0 No<\/td>\n<\/tr>\n
Akanksha Bangera<\/td>\n\u00a0\"\frac{5}{5}\"<\/span><\/td>\n\u00a0\"\frac{0}{5}\"<\/span><\/td>\n\u00a0\"\frac{2}{5}\"<\/span><\/td>\n\u00a0\u00a0Yes<\/td>\n<\/tr>\n
Rajesh Gaddanaker<\/td>\n\u00a0\"\frac{5}{5}\"<\/span><\/td>\n\u00a0\"\frac{3}{5}\"<\/span><\/td>\n\u00a0\"\frac{1}{5}\"<\/span><\/td>\n\u00a0\u00a0Yes<\/td>\n<\/tr>\n
guruprasad<\/td>\n\u00a0\"\frac{5}{5}\"<\/span><\/td>\n\u00a0\"\frac{2}{5}\"<\/span><\/td>\n\u00a0\"\frac{3}{5}\"<\/span><\/td>\n\u00a0 No<\/td>\n<\/tr>\n
Illa Durgesh<\/td>\n\u00a0\"\frac{5}{5}\"<\/span><\/td>\n\u00a0\"\frac{2}{5}\"<\/span><\/td>\n\u00a0\"\frac{3}{5}\"<\/span><\/td>\n\u00a0\u00a0Yes<\/td>\n<\/tr>\n
Murali Manohar<\/td>\n\u00a0\"\frac{12}{20}\"<\/span><\/td>\n\u00a0\"\frac{14}{20}\"<\/span><\/td>\n\u00a0\"\frac{-2}{5}\"<\/span><\/td>\n\u00a0\u00a0Yes<\/td>\n<\/tr>\n
Sandip Ingle Thakur<\/td>\n\u00a0\"\frac{6}{20}\"<\/span><\/td>\n\u00a0\"\frac{1}{20}\"<\/span><\/td>\n\u00a0\"\frac{4}{80}\"<\/span><\/td>\n\u00a0 No<\/td>\n<\/tr>\n
Niranjan Kannanugo<\/td>\n\u00a0\"\frac{5}{5}\"<\/span><\/td>\n\u00a0\"\frac{2}{5}\"<\/span><\/td>\n\u00a0\"\frac{2}{5}\"<\/span><\/td>\n\u00a0\u00a0Yes<\/td>\n<\/tr>\n
koushik<\/td>\n\u00a0\"\frac{15}{15}\"<\/span><\/td>\n\u00a0\"\frac{5}{15}\"<\/span><\/td>\n\u00a0\"\frac{6}{15}\"<\/span><\/td>\n\u00a0\u00a0Yes<\/td>\n<\/tr>\n
Isabella Dawn<\/td>\n\u00a0\"\frac{5}{5}\"<\/span><\/td>\n\u00a0\"\frac{5}{5}\"<\/span><\/td>\n\u00a0\"\frac{2}{5}\"<\/span><\/td>\n\u00a0 No<\/td>\n<\/tr>\n
Sachith Jaugar<\/td>\n\u00a0\"\frac{5}{5}\"<\/span><\/td>\n\u00a0\"\frac{2}{5}\"<\/span><\/td>\n\u00a0\"\frac{1}{5}\"<\/span><\/td>\n\u00a0\u00a0Yes<\/td>\n<\/tr>\n
Asad Inamdar<\/td>\n\u00a0\"\frac{10}{10}\"<\/span><\/td>\n\u00a0\"\frac{7}{9}\"<\/span><\/td>\n\u00a0\"\frac{4}{10}\"<\/span><\/td>\n\u00a0\u00a0Yes<\/td>\n<\/tr>\n
Sweety S<\/td>\n\u00a0\"\frac{15}{15}\"<\/span><\/td>\n\u00a0\"\frac{15}{15}\"<\/span><\/td>\n\u00a0\"\frac{3}{15}\"<\/span><\/td>\n\u00a0 No<\/td>\n<\/tr>\n
ramdas gavit<\/td>\n\u00a0\"\frac{15}{15}\"<\/span><\/td>\n\u00a0\"\frac{6}{10}\"<\/span><\/td>\n\u00a0\"\frac{4}{5}\"<\/span><\/td>\n\u00a0 Yes<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Table 1: A table showing snapshots of free mock exam sessions and TrustSpot reviews.<\/p>\n

 <\/p>\n

Choosing a ML technique – whether a user is a potential reviewer?<\/h3>\n

 <\/p>\n

Our requirement is to assess whether a user will rate mock-set-plus<\/a> on TrustSpot<\/a>. What we have is historical ratings from TrustSpot<\/a>. As we can see above, there are multiple factors (probably dependent) that contribute in a user’s decision to rate or not.<\/p>\n

– How many questions user attempted?<\/p>\n

– How much time a user has spent?<\/p>\n

– What is the score?<\/p>\n

The requirement for now is to connect historical trend to compute a probability of an outcome. We will use Naive-Bayes technique.<\/p>\n

 <\/p>\n

Preprocessing<\/h2>\n

 <\/p>\n

Let us categorize above data (table 1) into the following groups:<\/p>\n