Frequently Asked Questions
1. What should be the format of the technical report ?
The paper should be submitted in IJCAI style format with a maximum of 8 pages. Further information about the IJCAI format is available on the IJCAI website. There is also a IJCAI-2019 template on Overleaf.
2. Will we need to predict on both the datasets separately?
Yes. We will evaluate the two datasets (Friends, EmotionPush) separately.
3. What is the submission file format?
The submission file format is similar to the original dataset format, but with extra participant information.
See the Submission Template.
4. The instructions mention that "Participants will need to detect the emotion for each utterance among four label candidates: joy, sadness, anger, and neutral." However, the dataset contains 8 labels. Could you clarify?
Due to the limited number of three of the emotions (surprise, disgust, and fear) , we will only accept and evaluate utterances with the following labels: neutral, joy, sadness, anger. We will only accept submissions with these 4 labels.
5. Where can I access the EmotionX 2018 data files?
The data from EmotionX 2018 is available here.
6. How will I get the test data?
An email with links to the test data will be emailed to all participants on the release date.
7. What are the evaluation metrics for this year's contest?
As explained here, "the final evaluation, we will compute the precision, recall and F1-scores for each of the four labels, and then summarize using micro F1-score."
8. In the EmotionX 2018 competition, the evaluation metrics used per-class accuracy. What are per-class accuracies computed?
The per-class accuracy used in 2018 is equivalent to pre-class recall. See our sample calculation to for more information.
9. Will the technical papers be published?
The technical papers for this challenge will not be published/archived. However, we will upload them to the website for other workshop participants to view.
10. I put my code on Github. How can I share it?
You can add a link to the Github repository in your paper. Here are two possible phrases you can use in your LaTeX file:
The source code for our model is available as a Github repository\footnote{https://github.com/...}.The source code for our model is available as a Github repository at \texttt{https://github.com/...}
Once your report is available online, it's also a good idea to update your repository's README.md to include a link back to the report.