The Third International Workshop on Multimodal Learning Analytics will bring together researchers in multimodal interaction and systems, cognitive and learning sciences, educational technologies, and related areas to advance research on multimodal learning analytics. The Presentation Quality includes a data corpus that involves 130 oral presentations of Spanish-speaking undergraduate students in groups of 3 to 6 members presenting projects (entrepreneurship ideas, literature reviews, research designs, software design, etc.). Data were collected on their natural multimodal communication in regular classroom settings. The following data is available: speech, facial expressions and physical movements in video, skeletal data gathered from Kinect for each individual, and slide presentation files. In total, approximately 10 hours of multimodal data is available for analysis of these presentations. In addition grading for individuals when doing their presentations is included as well as a group-grade related to the quality of the slides used when doing each presentation.
The dataset is available to participants who wish to contribute at the Third International Workshop on Multimodal Learning Analytics grand challenge. This challenge seeks to solve the following questions:

  1. How multimodal techniques can help us in evaluating oral skills when doing presentations.
  2. How good is a group presentation based on the individual presentations and the quality of the slides used in a presentation.

Steps for MMLA participants:
  1. Read and sign the collaborator agreement document. Email it to the organizer at Once this has been submitted and your agreement has been approved by a workshop organizer (allow 48 hrs.), you will receive an email with password information to access the dataset and data description.
  2. Login with your MMLA workshop participant password to
  3. Download and read the document describing data.
  4. Download data for your MMLA grand challenge analyses. This data is available at this address and comprises # multimodal data groups. Each of the session contains 4 different data types:
    1. Videos (High and Low quality).
    2. Audios (Two resources).
    3. Kinect skeleton files.
    4. Human coding for oral presentations.
  5. Use any tool of your choice to analyze the data.