Recommender systems challenge 2014

Abstract

The 2014 ACM Recommender Systems Challenge invited researchers and practitioners to work towards a common goal, this goal being the prediction of users engagement in movie ratings expressed on Twitter. More than 200 participants sought to join the challenge and work on the new dataset released in its scope. The participants were asked to develop new algorithms to predict user engagement and evaluate them in a common setting, ensuring that the comparison was objective and unbiased in the setting of the challenge.

http://www.sersc.org/journals/IJSEIA/vol11_no7_2017/1.pdf

“…New real world systems require results to be calculated in real time to use the results with the current system's user. The interest prediction of users is a challenging task [15].…”

Spreading the news

“…We then extract a set of user features and tweet/content features and represent each tweet as a feature vector to be used in our prediction of audience engagement, which we operationalize as retweets received (a commonly used measure of engagement, see e.g., [21]). We explore several regression methods to find the key features that predict audience engagement and assess the relative importance of these features with respect to each of the news categories.…”

Utilizing Voting Systems for Ranking User Tweets

“…The Dataset used in this research is the extended movie tweeting dataset [16] publicly published by the RecSys Challenge 2014 [17,18]. The dataset consists of 170,285 tweets, contains ratings on movies and published by users of IMDB iOS app.…”