Competition

Troll Meme classification in Tamil

Organized by dravidianlangtech - Current server time: March 30, 2025, 9:37 a.m. UTC

First phase

First phase
Nov. 20, 2020, midnight UTC

End

Competition Ends
Jan. 15, 2021, 8:07 a.m. UTC

Traditional media such as television, radio and newspaper are monitored and scrutinized for their content. However, social media platforms facilitate internet users to interact and contribute to their online community without any moderation. Although most of the time, these internet users are harmless, some tend to produce offensive content due to anonymity and freedom provided by social networks. Memes have become an integrated part of online communication due to the ability to self-replicate and propagate across cultures. Most of these memes tend to be funny, but sometimes they might cross their limit to become offensive to specific individuals or groups, such memes could be referred to as troll memes. The use case of this shared task is to bring people to discuss these issues of trolling and study the problem to solve it systematically.

We accept test result only through google form.
Format of the submission file should be like below:
 
 
 
imagename label
test_img_1 not_troll
test_img_2 troll
test_img_3

troll
  • label column should only have labels in the form of "troll" or "not_troll"
  • imagename should have same sequence as mentioned in the test_captions.csv
Submission should be a zip file with your team name containing a csv file with name 'teamname.csv'. The submission will be evaluated with weighted average F1-score. Submit results in google form.

Please fill out the form to submit the result.

Classification system’s performance will be measured in terms of weighted averaged F-Score across all the classes. Weighted averaged are averaging the support-weighted mean per label. Participants are encouraged to check their system with Sklearn classification report https://scikit-learn.org/stable/modules/generated/sklearn.metrics.classification_report.html

Terms and Conditions

By downloading the data or by accessing it any manner, you agree not to redistribute the data except for non-commercial and academic-research purposes. The data must not be used for providing surveillance, analyses or research that isolates a group of individuals or any single individual for any unlawful or discriminatory purpose.

You should cite these papers if you are using our data.

@inproceedings{suryawanshi-etal-2020-dataset,
    title = "A Dataset for Troll Classification of {T}amil{M}emes",
    author = "Suryawanshi, Shardul  and
      Chakravarthi, Bharathi Raja  and
      Verma, Pranav  and
      Arcan, Mihael  and
      McCrae, John Philip  and
      Buitelaar, Paul",
    booktitle = "Proceedings of the WILDRE5{--} 5th Workshop on Indian Language Data: Resources and Evaluation",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://www.aclweb.org/anthology/2020.wildre-1.2",
    pages = "7--13",
    abstract = "Social media are interactive platforms that facilitate the creation or sharing of information, ideas or other forms of expression among people. This exchange is not free from offensive, trolling or malicious contents targeting users or communities. One way of trolling is by making memes, which in most cases combines an image with a concept or catchphrase. The challenge of dealing with memes is that they are region-specific and their meaning is often obscured in humour or sarcasm. To facilitate the computational modelling of trolling in the memes for Indian languages, we created a meme dataset for Tamil (TamilMemes). We annotated and released the dataset containing suspected trolls and not-troll memes. In this paper, we use the a image classification to address the difficulties involved in the classification of troll memes with the existing methods. We found that the identification of a troll meme with such an image classifier is not feasible which has been corroborated with precision, recall and F1-score.",
    language = "English",
    ISBN = "979-10-95546-67-2",
}

 @inproceedings{dravidiantrollmeme-eacl,
  title={Findings of the Shared Task on {T}roll {M}eme {C}lassification in {T}amil},
  author={Suryawanshi, Shardul and
Chakravarthi, Bharathi Raja},
    booktitle = "Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages",
    month = April,
    year = "2021",
    publisher = "Association for Computational Linguistics",
year={2021}
}

Task announcement: Nov 20, 2020
Release of Trial data: Nov 20, 2020
Release of Training data: Nov 30
Release of Test data: Jan 2, 2021
Run submission deadline: Jan 10, 2021
Results declared: Jan 15, 2021

Paper submission: Jan 30, 2021
Peer review notification: Feb 18, 2021
Camera-ready paper due: Feb 24, 2021
Workshop Dates: April 19-20, 2021

Shardul Suryawanshi, Data Science Institute, National University of Ireland Galway, email: shardul.suryawanshi@insight-centre.org
Bharathi Raja Chakravarthi, Data Science Institute, National University of Ireland Galway
Mihael Arcan, Data Science Institute, National University of Ireland Galway
Paul Buitaleer, Data Science Institute, National University of Ireland Galway

First phase

Start: Nov. 20, 2020, midnight

Competition Ends

Jan. 15, 2021, 8:07 a.m.

You must be logged in to participate in competitions.

Sign In