TY - GEN
T1 - Disambiguation of features for improving target class detection from social media text
AU - Chiroma, Fatima Modibbo
AU - Haig, Ella
PY - 2020/8/26
Y1 - 2020/8/26
N2 - The rise of social media has led to an abundance of textual data, as well as the rise of unhealthy behaviours targeted at others (e.g. bullying, hate speech) or at oneself (e.g. suicide). In recent years, machine learning approaches have been employed to detect such behaviours, which tend to constitute a small portion of the social media content and need to be distinguished from other discourse on social media that may discuss such behaviours without displaying that behaviour, e.g. social media posts about helping people who may be at risk of suicide, thus, making this a very challenging task. In the context of machine learning, such behaviours are referred to as target classes, i.e. the main behaviours to be detected. In this paper we proposed an approach for disambiguation of features in relation to their membership to the target class vs. non-target class(es). We validate our approach with a case study on suicide detection and our results show that the proposed disambiguation approach leads to a better detection rate of suicide.
AB - The rise of social media has led to an abundance of textual data, as well as the rise of unhealthy behaviours targeted at others (e.g. bullying, hate speech) or at oneself (e.g. suicide). In recent years, machine learning approaches have been employed to detect such behaviours, which tend to constitute a small portion of the social media content and need to be distinguished from other discourse on social media that may discuss such behaviours without displaying that behaviour, e.g. social media posts about helping people who may be at risk of suicide, thus, making this a very challenging task. In the context of machine learning, such behaviours are referred to as target classes, i.e. the main behaviours to be detected. In this paper we proposed an approach for disambiguation of features in relation to their membership to the target class vs. non-target class(es). We validate our approach with a case study on suicide detection and our results show that the proposed disambiguation approach leads to a better detection rate of suicide.
KW - Term disambiguation
KW - Text classification
KW - Suicide-related communications
KW - Social media text
UR - https://wcci2020.org/
U2 - 10.1109/FUZZ48607.2020.9177778
DO - 10.1109/FUZZ48607.2020.9177778
M3 - Conference contribution
SN - 978-1-7281-6933-0
T3 - Proceedings of the 2020 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
BT - Proceedings of the 2020 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
PB - Institute of Electrical and Electronics Engineers
T2 - 2020 IEEE International Conference on Fuzzy Systems
Y2 - 19 July 2020 through 24 July 2020
ER -