What is viability?
Have you ever experienced a team collaboration that felt toxic and ultimately fell apart? How quickly did you know that it would end poorly?
Studying team viability helps answer those questions. Team viability is the capacity of a team for sustainable growth and future success.
It captures both the team's members satisfaction and their intent to remain in the team.
Is team viability related to team performance?
It varies. For routine activities, team viability and team performance have a strong and positive relationship. However, for more complex activities, the relationship between team viability and performance weakens. For example, high performance teams can still suffer from low viability.
Classify viability from chat transcripts!
Your data will be evaluated by three logistic regression models trained at the 10th, 50th and 90th viability percentile.
Choose a data format or upload a json/csv to classify the team's viability.
The only required fields are message and user. The time field is optional.
We estimate this team's viability will be higherlower than the 10th percentile's
We estimate this team's viability will be higherlower than the 50th percentile's
We estimate this team's viability will be higherlower than the 90th percentile's
Your data is not saved but only evaluated. The classification provided above was done using a pretrained logistic regression models. It is provided only for educational purposes and should not be used as the basis for any professional/commercial use. Read more on the limitations in the accompanying paper here
Abstract
Understanding team viability — a team’s capacity for sustained and future success — is essential for building effective teams. In this study, we aggregate features drawn from the organizational behavior literature to train a viability classification model over a dataset of 669 10-minute text conversations of online teams. We train classifiers to identify teams at the top decile (most viable teams), 50th percentile (above a median split), and bottom decile (least viable teams), then characterize the attributes of teams at each of these viability levels. We find that a lasso regression model achieves an accuracy of .74–.92 AUC ROC under different thresholds of classifying viability scores. From these models, we identify the use of exclusive language such as ‘but’ and ‘except’, and the use of second person pronouns, as the most predictive features for detecting the most viable teams, suggesting that active engagement with others’ ideas is a crucial signal of a viable team. Only a small fraction of the 10-minute discussion, as little as 70 seconds, is required for predicting the viability of team interaction. This work suggests opportunities for teams to assess, track, and visualize their own viability in real time as they collaborate.
Cite us!
Download the paper here, and cite this work as:
Hancheng Cao, Vivian Yang, Victor Chen, Yu Jin Lee, Lydia Stone, N'godjigui Junior Diarrassouba, Mark E. Whiting, and Michael S. Bernstein. 2020. My Team Will Go On: Differentiating High and Low Viability Teams through Team Interaction. Proc. ACM Hum.-Comput. Interact. 4, CSCW3, Article 230 (December 2020), 27 pages. https://doi.org/10.1145/3432929Or with BibTex:
@article{cao2020my,
author = {Cao, Hancheng and Yang, Vivian and Chen, Victor and Lee, Yu Jin and Stone, Lydia and Diarrassouba,
N'godjigui Junior and Whiting, Mark E. and Bernstein, Michael S.},
title = {My Team Will Go On: Differentiating High and Low Viability Teams through Team Interaction},
year = {2020},
issue_date = {December 2020},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {4},
number = {CSCW3},
url = {https://doi.org/10.1145/3432929},
doi = {10.1145/3432929},
journal = {Proc. ACM Hum.-Comput. Interact.},
month = December,
articleno = {230}, numpages = {27}
}
