## Motivation ##
Perhaps the most critical, strategic, and an enduring asset that a corporation possesses is its reputation. Although corporate reputation is undoubtedly a significant and relevant corporate asset, formidable measurement challenges exist nowadays. We propose the creation of a "reputation index" based on public articles and all media resources, which are accessed on the internet and are relevant to the particular company.

Our approach is based on a Sentiment analysis strategy to evaluate all the events related to the company and its employees, client's opinion and calculate the general index, which can define the level of the reputation.
Several studies have focused on the same topic of the sentiment changes overtime in online media. Gilbert & Karahalios (2010) have estimated information about future stock market prices based on the analysis of the emotions expressed in blogs. Based on over 20 million posts made on the site LiveJournal, they found that increases in expressions of anxiety predict downward pressure on the S&P 500 index. O´Connor et al. (2010) have found that a relatively simple sentiment detector based on Twitter data replicates consumer confidence and presidential job approval polls.

## Task ##
We propose to combine Sentiment analysis and Entities recognition methods to find the 10 most positive and 10 most negative files about each of the 2 proposed companies: Keppel (Keppel Corporation Limited) and Prudential (Prudential Assurance Company).

## Hints ##
Natural Language Processing methods as: Sentiment analysis, Entities recognition and Text summarization should be used in this competition.

## Evaluation ##
In order to explore the feasibility of automating reputation analysis processes, we have implemented a prototype system that calculates the reputation index in newspaper articles.
The prototype has been used to find the files with the best/worst opinion about the companies.

## Team ##
We will only consider teams of 1 or 2.

## Prize ##
**To be eligible for prizes, you must be an EPFL student, or have graduated from EPFL in the last 6 months as this is an internal competition.**

 - The winning team will be awarded 2 return tickets from Geneva to Singapore. But also, if you so choose to apply for an internship/master's project with us at **Dathena**, we will consider that you passed the technical interview, hence you will only interview with the HR department.
 - The 2nd best team will be awarded 2 Bose Headphones
 - The 3rd best team will be awarded a Nespresso machine

## Questions ##
If you have any questions, please send an email to `romain.choukroun@dathena.io` or `guillaume.mollard@dathena.io`