Authorship analysis deals with the classification of texts into classes based on the stylistic choices of their authors. Beyond the author identification and author verification tasks where the style of individual authors is examined, author profiling distinguishes between classes of authors studying their sociolect aspect, that is, how language is shared by people. This helps in identifying profiling aspects such as gender, age, native language, or personality type. Author profiling is a problem of growing importance in applications in forensics, security, and marketing. E.g., from a forensic linguistics perspective one would like being able to know the linguistic profile of the author of a harassing text message (language used by a certain type of people) and identify certain characteristics (language as evidence). Similarly, from a marketing viewpoint, companies may be interested in knowing, on the basis of the analysis of blogs and online product reviews, the demographics of people that like or dislike their products. The focus is on author profiling in social media since we are mainly interested in everyday language and how it reflects basic social and personality processes.
This year the focus will be on gender identification in Twitter, where text and images may be used as information sources. The languages addressed will be:
Download corpus (Updated February 27, 2018)
Your software must take as input the absolute path to an unpacked dataset, and has to output for each document of the dataset a corresponding XML file that looks like this:
<author id="author-id" lang="en|es|ar" gender_txt="male|female" gender_img="male|female" gender_comb="male|female" />
We ask you to provide with three different predictions for the author's gender depending on your approach:
As previously said, you can participate in both textual and images classification, or only in one of them. Hence, if your approach uses only textual features, your prediction should be given in gender_txt. Similarly, if your approach relies on images, your prediction should be given in gender_img. In case you use both text and images, your prediction should be given in gender_comb. Furthermore, in such a case, if you can provide also the prediction by using both approaches separately, this would allow us to perform a more in-depth analysis of the results and to compare textual vs. image based author profiling. In this case, you should provide for the same author the three predictions: gender_txt, gender_img and gender_comb.
The naming of the output files is up to you, we recommend to use the author-id as filename and "xml" as extension.
IMPORTANT! Languages should not be mixed. A folder should be created for each language and place inside only the files with the prediction for this language.
The performance of your author profiling solution will be ranked by accuracy.
For each language, we will calculate individual accuracies. Then, we will average the accuracy values per language to obtain the final ranking.
We ask you to prepare your software so that it can be executed via command line calls.
You can choose freely among the available programming languages and among the operating systems Microsoft Windows and Ubuntu. We will ask you to deploy your software onto a virtual machine that will be made accessible to you after registration. You will be able to reach the virtual machine via ssh and via remote desktop. More information about how to access the virtual machines can be found in the user guide below:
Once deployed in your virtual machine, we ask you to access TIRA at www.tira.io, where you can self-evaluate your software on the test data.
Note: By submitting your software you retain full copyrights. You agree to grant us usage rights only for the purpose of the PAN competition. We agree not to share your software with a third party or use it for other purposes than the PAN competition.
We refer you to: