The year is 1050 BC near the warm beaches of the Mediterranean Sea. The Martians have invaded. It is a time when earthlings have to unite against the colonial Martians who are conspiring against us to take over the planet. The Martians can time travel too! They travel to the year 1997 to a small town in the United Kingdom and pick up three things, an English Grammar book, Good-Turing’s paper, and newspapers from a local market. Their aim is to destroy Earth retroactively. They come back to the year 1050 BC and alter everything in Earthling’s civilizations history to make them never land on Mars, their beloved land. 
Modern day language and the alphabet was in the formative stages in 1050 BC. The Phoenician alphabet is the oldest verified consonantal alphabet. The Martians now have a diabolical plan. They want to spread nonsensical news amongst the Phoenicians for them to believe this nonsensical news is valid language. If language had never developed, do you think humans could have ever sent out missions to Mars? 
The one thing Martians are good at is statistics (They do have Good-Turing’s paper after all). They develop a trigram language model using the GT paper, which they will use to generate nonsensical news in the Phoenician alphabet using the newspapers they picked up from the year 1997. You are a local in Greece, and an independent researcher, who wants to stop the martians from succeeding by removing all the fake articles from circulation. Your job is to distinguish between the fake and real articles that are being circulated in your town by using your statistics knowledge which Prof. Bhiksha has taught you in your dreams. (Well, CMU 11-761 Fall 2018 course has a dream edition too).
Here are the files at your disposal:
The following files can be found in the data section of kaggle:
corpus
The collection of newpapers the Martians took from 1997 in the Phoenician alphabet. You may use this to build your own language models.
trainingSet
1000
    articles, 500 real and 500 fake, of varying lengths.
Articles are separated by the separator `~~~~~'.
The tags <s> and </s> represent begin and end of sentence,
    respectively.
trainingSetLabels
Contains the correct labels for
trainingSet
.  A `0' means the
    article is fake and `1' means it is real.
developmentSet
Contains 200 articles, 100 real and 100 fake, in the same format as
trainingSet
.
Note:
Articles were truncated
to meet the following length
(#
    of sentences)
distribution for each category:
Number of sentences
Number of articles with this number of sentences
1
20
2
10
3
10
4
10
5
10
7
10
10
10
15
10
20
10
[
Note: the set on which you will be tested ("test
    set") will have the same format, approximately the same number of real and fake articles, and the same length distributions as this development set. 
    Of course, the shorter the truncated article, the harder the classification
    decision.]
developmentSetLabels
Contains the correct labels for
developmentSet
, in the same
    format as
trainingSetLabels
.
testSet
The format is the same as in trainingSet and developmentSet. You are required to submit your final predictions on this testSet. Your output file must contain 200 lines with predictions (0/1)