Mortality Classification

User-generated content is central to social computing scholarship. However, researchers and practitioners often presume that these users are alive. Failing to account for mortality is problematic in social media where an increasing number of profiles represent those who have died. Identifying mortality can empower designers to better manage content and support the bereaved, as well as promote high-quality data science. Based on a computational linguistic analysis of post-mortem social media profiles and content, we report on classifiers developed to detect mortality and show that mortality can be determined after the first few occurrences of post-mortem content. Applying our classifiers to content from two other platforms also provided good results. Finally, we discuss trade-offs between models that emphasize pre- vs. post-mortem precision in this sensitive context. These results mark a first step toward identifying mortality at scale, and show how designers and scientists can attend to mortality in their work.

Publications

1. CSCW

   Tending Unmarked Graves: Classification of Post-mortem Content on Social Media Jialun "Aaron" Jiang and Jed R. Brubaker
   Proceedings of the ACM on Human-Computer Interaction 2, CSCW: Article 81

   • Abstract
   • PDF
   • Reference
   • BibTeX
   • DOI: 10.1145/3274350
   Jialun "Aaron" Jiang and Jed R. Brubaker. 2018. Tending Unmarked Graves: Classification of Post-mortem Content on Social Media. Proceedings of the ACM on Human-Computer Interaction 2, CSCW: Article 81. https://doi.org/10.1145/3274350

   @article{Jiang2018-ripgenre,
     title = {Tending {Unmarked} {Graves}: {Classification} of {Post}-mortem {Content} on {Social} {Media}},
     volume = {2},
     number = {CSCW},
     journal = {Proceedings of the ACM on Human-Computer Interaction},
     author = {Jiang, Jialun "Aaron" and Brubaker, Jed R.},
     year = {2018},
     pages = {Article 81},
     doi = {10.1145/3274350},
     tags = {death-sns, mortality-classification}
   }
   

   User-generated content is central to social computing scholarship. However, researchers and practitioners often presume that these users are alive. Failing to account for mortality is problematic in social media where an increasing number of profiles represent those who have died. Identifying mortality can empower designers to better manage content and support the bereaved, as well as promote high-quality data science. Based on a computational linguistic analysis of post-mortem social media profiles and content, we report on classifiers developed to detect mortality and show that mortality can be determined after the first few occurrences of post-mortem content. Applying our classifiers to content from two other platforms also provided good results. Finally, we discuss trade-offs between models that emphasize pre- vs. post-mortem precision in this sensitive context. These results mark a first step toward identifying mortality at scale, and show how designers and scientists can attend to mortality in their work.

2. ICWSMPoster

   Describing and Classifying Post-Mortem Content on Social Media Jialun "Aaron" Jiang and Jed Brubaker
   International AAAI Conference on Web and Social Media (ICWSM 2018)

   • Abstract
   • PDF
   • Reference
   • BibTeX
   • DOI: 10.1609/icwsm.v12i1.15048
   Jialun "Aaron" Jiang and Jed Brubaker. 2018. Describing and Classifying Post-Mortem Content on Social Media. In International AAAI Conference on Web and Social Media (ICWSM 2018). https://doi.org/10.1609/icwsm.v12i1.15048

   @inproceedings{Jiang2018ICWSM,
     author = {Jiang, Jialun "Aaron" and Brubaker, Jed},
     title = {Describing and Classifying Post-Mortem Content on Social Media},
     booktitle = {International AAAI Conference on Web and Social Media (ICWSM 2018)},
     year = {2018},
     keywords = {death; social media; myspace; machine learning; computational linguistics},
     tags = {death-sns, mortality-classification},
     doi = {10.1609/icwsm.v12i1.15048},
     pubtype = {Poster}
   }
   

   As the quantity of user profiles on social media grows, so does the number of post-mortem profiles. In this paper, we present a computational linguistic analysis of post-mortem social media profiles. Specifically, we provide an analysis of pre- vs. post-mortem language use, followed by a description of classifiers we developed that can accurately classify the mortality of social media profiles. These results shed initial lights into the ways in which people speak to the dead, and mark a first step toward accurately identifying mortality on a large scale.

Blog

• Tending Unmarked Graves: Automatic Identification of Post-mortem Content on Social Media Aaron Jiang · October 19, 2018