Submission Instructions

All paper submissions and reviews will be handled electronically in PDF format. ACM Recommender Systems 2012 submissions should be prepared according to the standard ACM SIG proceedings format. For your convenience, we provide paper templates in Microsoft Word and LaTeX:

• Microsoft Word document template
• LaTeX style file and a sample document showing how to use it
• PDF sample document showing what your submission should look like

ACM Recommender Systems 2012 will not use double-blind review, so please include authors' names and affiliations on your submission.

Submitting your paper

Long and Short papers (see Call for Papers for details) should be submitted in PDF format via EasyChair submission system. If you have used easychair before, you may use your existing username and password. Otherwise please create a new easychair account.

Abstracts are due on April 2. They should be short, like the abstract that will eventually be in the paper. You can change the abstract and the author list, and resubmit a new version of the paper, any time up until the paper submission deadline on April 9. The purpose of the abstracts is to allow the program committee to start assigning papers for review, so that reviewing can begin soon after April 9.

Each submission will be reviewed by at least three members of the program committee.

Submissions to workshops are due by May 25. Please follow the submission instructions on the web pages for the individual workshops.

Evaluation criteria

Below, you can find a set of examples of evaluation criteria for different types of papers from past RecSys conferences, which may help you preparing your submission.

Algorithms papers: A good algorithms paper will:

• describe the recommender/ranking/prediction algorithm in sufficient detail that someone else could implement it
• articulate the important new idea(s) that the algorithm instantiates, in comparison to previously known algorithms
• demonstrate that performance is better on some well-defined metric, than some baseline algorithm.

Applications: A good RecSys paper reporting on a case study of an application deployment will:

• Identify a novel type of item to be recommended or decision process to be influenced, in comparison to previously reported targets of recommender systems
• Identify unusual properties of the new item type that created special problems or opportunities
• Report on challenges and how they were overcome
• Explain any non-trivial mappings of known techniques to the new domain
• Articulate lessons that might be relevant to others deploying Recommender Systems in similar or related contexts

Presentation techniques: A good RecSys paper about a new way of using recommendations/prediction/ranking to enhance the user experience will:

• Clearly explain the presentation technique
• Articulate what is novel about it, in comparison to existing techniques
• Demonstrate that it has desirable properties for users, through anecdotes or data from lab studies or field deployment

Recommender Inputs: A good RecSys paper about a new source of information to be used as an input to recommender algorithms will:

• Clearly explain how the information will be gathered or elicited
• Articulate what is novel about the information source, in comparison to other sources
• Provide some evidence that it can be used to make good recommendations