Data Set Information:

The Dataset is uploaded in ZIP format. The dataset contains 5 variants of the dataset, for the details about the variants and detailed analysis read and cite the research paper

@INPROCEEDINGS{Sing1503:Comment,
AUTHOR='Kamaljot Singh and Ranjeet Kaur Sandhu and Dinesh Kumar',
TITLE='Comment Volume Prediction Using Neural Networks and Decision Trees',
BOOKTITLE='IEEE UKSim-AMSS 17th International Conference on Computer Modelling and
Simulation, UKSim2015 (UKSim2015)',
ADDRESS='Cambridge, United Kingdom',
DAYS=25,
MonTH=mar,
YEAR=2015,
KEYWORDS='Neural Networks; RBF Network; Prediction; Facebook; Comments; Data Mining;
REP Tree; M5P Trees.',
ABSTRACT='The leading treads towards social networking services had drawn massive
public attention from last one and half decade. The amount of data that is
uploaded to these social networking services is increasing day by day. So,
there is massive requirement to study the highly dynamic behavior of users
towards these services. This is a preliminary work to model the user
patterns and to study the effectiveness of machine learning predictive
modeling approaches on leading social networking service Facebook. We
modeled the user comment patters, over the posts on Facebook Pages and
predicted that how many comments a post is expected to receive in next H
hrs. In order to automate the process, we developed a software prototype
consisting of the crawler, Information extractor, information processor and
knowledge discovery module. We used Neural Networks and Decision Trees,
predictive modeling techniques on different dataset variants and evaluated
them under Hits(at)10 (custom measure), Area Under Curve, evaluation Time
and Mean Absolute error evaluation metrics. We concluded that the Decision
trees performed better than the Neural Networks under light of all
evaluation metrics.'
}



The research paper is also available at conference website:

uksim.info/uksim2015/[Web link]


another extended paper is that is to be published soon is :

@ARTICLE{Sing1601:Facebook,
AUTHOR='Kamaljot Singh',
TITLE='Facebook Comment Volume Prediction',
JOURNAL='International Journal of Simulation- Systems, Science and Technology-
IJSSST V16',
ADDRESS='Cambridge, United Kingdom',
DAYS=30,
MonTH=jan,
YEAR=2016,
KEYWORDS='Neural Networks; RBF Network; Prediction; Facebook; Comments; Data Mining;
REP Tree; M5P Trees.',
ABSTRACT='The amount of data that is uploaded to social networking services is
increasing day by day. So, their is massive requirement to study the highly
dynamic behavior of users towards these services. This work is to model the
user patterns and to study the effectiveness of machine learning predictive
modeling approaches on leading social networking service Facebook. We
modeled the user comment patters, over the posts on Facebook Pages and
predicted that how many comments a post is expected to receive in next H
hrs. To automate the process, we developed a software prototype consisting
of the crawler, Information extractor, information processor and knowledge
discovery module. We used Neural Networks and Decision Trees, predictive
modeling techniques on different data-set variants and evaluated them under
Hits(at)10, Area Under Curve, evaluation Time and M.A.E metrics. We
concluded that the Decision trees performed better than the Neural Networks
under light of all metrics.'
}


this above paper will be freely available after publication at www.ijssst.info

Attribute Information:

1
Page Popularity/likes
Decimal Encoding
Page feature
Defines the popularity or support for the source of the document.


2
Page Checkinsa€?s
Decimal Encoding
Page  feature
Describes how many individuals so far visited this place. This feature is only associated with the places eg:some institution, place, theater etc.


3
Page talking about
Decimal Encoding
Page feature
Defines the daily interest of individuals towards source of the document/ Post. The people who actually come back to the page, after liking the page. This include activities such as comments, likes to a post, shares, etc by visitors to the page.


4
Page Category
Value  Encoding
Page feature
Defines the category of the source of the document eg: place, institution, brand etc.


5 - 29
Derived
Decimal  Encoding
Derived feature
These features are aggregated by page, by calculating min, max, average, median and standard deviation of essential features.


30
CC1
Decimal Encoding
Essential feature
The total number of comments before selected base date/time.


31
CC2
Decimal Encoding
Essential feature
The number of comments in last 24 hours, relative to base date/time.


32
CC3
Decimal Encoding
Essential feature
The number of comments in last 48 to last 24 hours relative to base date/time.


33
CC4
Decimal Encoding
Essential feature
The number of comments in the first 24 hours after the publication of post but before base date/time.


34
CC5
Decimal Encoding
Essential feature
The difference between CC2 and CC3.


35
base time
Decimal(0-71) Encoding
Other feature
Selected time in order to simulate the scenario.


36
Post length
Decimal Encoding
Other feature
Character count in the post.


37
Post Share Count
??????Decimal Encoding
Other feature
This features counts the no of shares of the post, that how many peoples had shared this post on to their timeline.


38
Post Promotion Status
??????Binary Encoding
Other feature
To reach more people with posts in News Feed, individual promote their post and this features tells that whether the post is promoted(1) or not(0).


39
H Local
???Decimal(0-23) Encoding
Other feature
This describes the H hrs, for which we have the target variable/ comments received.


40-46
Post published weekday
Binary Encoding
Weekdays feature
This represents the day(Sunday...Saturday) on which the post was published.


47-53
base DateTime weekday
Binary Encoding
Weekdays feature
This represents the day(Sunday...Saturday) on selected base Date/Time.

54
Target Variable
Decimal
Target
The no of comments in next H hrs(H is given in Feature no 39).

Relevant Papers:

Provide references to papers that have cited this data set in the past (if any).The Dataset is uploaded in ZIP format. The dataset contains 5 variants of the dataset, for the details about the variants and detailed analysis read and cite the research paper

@INPROCEEDINGS{Sing1503:Comment,
AUTHOR='Kamaljot Singh and Ranjeet Kaur Sandhu and Dinesh Kumar',
TITLE='Comment Volume Prediction Using Neural Networks and Decision Trees',
BOOKTITLE='IEEE UKSim-AMSS 17th International Conference on Computer Modelling and
Simulation, UKSim2015 (UKSim2015)',
ADDRESS='Cambridge, United Kingdom',
DAYS=25,
MonTH=mar,
YEAR=2015,
KEYWORDS='Neural Networks; RBF Network; Prediction; Facebook; Comments; Data Mining;
REP Tree; M5P Trees.',
ABSTRACT='The leading treads towards social networking services had drawn massive
public attention from last one and half decade. The amount of data that is
uploaded to these social networking services is increasing day by day. So,
there is massive requirement to study the highly dynamic behavior of users
towards these services. This is a preliminary work to model

Kamaljot Singh, Assistant Professor, Lovely Professional University, Jalandhar.
Kamaljotsingh2009 '@' gmail.com