Context I m writing a paper on HR analyitcs. In this case we want to find out id we can predict (before it happens) what employees will suffer from absenteeism (due to work accident, or the flu or some common sickness) by looking at their comments and likes islike sin a company private forum and their daily ratings their feelings about their work... which cna be positve negative or neutral. IS it possible? If you make a good EDA I will contact you to become co author. ## Content Inside this dataset you will find various files: And previous papers on other parts of the dataset can be found here: https://myhappyforce.com/employee_turnover_paper.pdf Considerations: -Employees are only allowed to participate once a day. -An employee can give either a like or a dislike to a comment but not both. -On some companies, they are allow to reply to comments of their peers. -We don't have demographics on Happyforce: so no hiring date or turnover date is available on the dataset. Only account deletion date is available. Company.csv: A listing of all companies available on the dataset -companyAlias: Id of the company on the dataset. -creationDate: Creation date of the account. -type: Industry type. -status: Status of the account (ACTIVE or PAUSED/BLOCKED => no more a customer of HF). Votes.csv: A listing of all votes registered on Happyforce to the question "How are you today?" from the employees on the dataset. -employee: Id of the employee on the dataset -companyAlias: Id of the company on the dataset. -voteDate:When the vote was been posted. -vote: Which was the vote of the employee (de 1 a 4: Very Bad, Bad, Good, Very Good) LastParticipationExists.csv: A listing of all employees of the companies on the dataset. Their status on the system and some useful information. -employee: Id of the employee on the dataset -companyAlias: Id of the company on the dataset. -numVotes: Number of votes emited by this employee. -lastParticipationDate: Date of the last participation on HF. -stillExists: Has been this employee been removed from the HF? -deletedOn: When it was removed from Happyforce (Note: not all the entries have these information since that feature was added later) Comments.csv: A listing of all coments registered by the employees on the dataset. -employee: Id of the employee on the dataset -companyAlias: Id of the company on the dataset. -commentId: Id of the comment on the dataset. -commentLenght: Length of the comment -likes: Number of "agrees" received -dislikes: Number of "disagrees" received -commentDate: Date of the comment -feedbackType: When the employees submit a comment, they have to chose between 4 categories: INFORMATION, CONGRATULATION, SUGGESTION or SOMETHING IS WRONG (note: not all the entries have these information since that feature was added later) CommentInteractions.csv: -employee: Id of the employee on the dataset performing the interaction. -companyAlias: Id of the company on the dataset. -commentId: Id of the comment on the dataset. -interaction: Which Interaction is performed -1 -> disagree / 1 agree / 2 reply. -actionDate: When the interaction was performed. Acknowledgements data privided by myhappyforce Inspiration Lets make HR analytics cool Your data will be in front of the world's largest data science community. What questions do you want to see answered?