Prasadith Kirinde - Academia.edu (original) (raw)

Papers by Prasadith Kirinde

Research paper thumbnail of Multi-Task Learning to Capture Changes in Mood Over Time

Proceedings of the Eighth Workshop on Computational Linguistics and Clinical Psychology

Research paper thumbnail of Multi-Task, Multi-Channel, Multi-Input Learning for Mental Illness Detection using Social Media Text

Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019), 2019

We investigate the impact of using emotional patterns identified by the clinical practitioners an... more We investigate the impact of using emotional patterns identified by the clinical practitioners and computational linguists to enhance the prediction capabilities of a mental illness detection (in our case depression and posttraumatic stress disorder) model built using a deep neural network architecture. Over the years, deep learning methods have been successfully used in natural language processing tasks, including a few in the domain of mental illness and suicide ideation detection. We illustrate the effectiveness of using multitask learning with a multi-channel convolutional neural network as the shared representation and use additional inputs identified by researchers as indicatives in detecting mental disorders to enhance the model predictability. Given the limited amount of unstructured data available for training, we managed to obtain a task-specific AUC higher than 0.90. In comparison to methods such as multi-class classification, we identified multi-task learning with multi-channel convolution neural network and multiple-inputs to be effective in detecting mental disorders.

Research paper thumbnail of Mental Illness and Suicide Ideation Detection Using Social Media Data

Mental disorders and suicide have become a global public health problem. Over the years, research... more Mental disorders and suicide have become a global public health problem. Over the years, researchers in computational linguistics have extracted features from social media data for the early detection of users susceptible to mental disorders and suicide ideation. Lack of reliable and inadequate data and the requirement of interpretability can be identified as the principal reasons for the low adoption of neural network architectures in recognizing individuals with mental disorders and suicide ideation. In recent years, a gradual increase in the use of deep neural network architectures in detecting mental disorders and suicide ideation with low false positive and false negative rates became feasible. Our research investigates the efficacy of using a shared representation to learn lower-level features mutual among mental disorders and between mental disorders and suicide ideation. In addition to discovering the shared features between users with suicidal thoughts and users who self-declared a single mental disorder, we further investigate the impact of comorbidities on suicide ideation and use two unseen datasets to investigate the generalizability of the trained models. We use data from two different social media platforms to identify if knowledge can be shared between suicide ideation and mental illness detection tasks across platforms. Through multiple experiments with different but related tasks, we demonstrate the effectiveness of multi-task learning (MTL) when predicting users with mental disorders and suicide my journey to become a researcher and supporting me exceedingly throughout these years. I am incredibly thankful to my kids Thevinshya, Thevinya and Partheeshan, for their understanding of the time and energy I had to contribute throughout the years. I am ever grateful to my mother Turin, my father Piyasena and my sister Chaminie for encouraging my journey in the pursuit of knowledge and my father-in-law Karunagaran and my mother-in-law Nagulambigai for their continuous support. Great thanks to my labmate Ehsan Amjadian for being an amazing friend throughout the years. Through our insightful discussions over the years, I gained a wealth of knowledge about NLP and machine learning. I would like to give my heartful gratitude to all my lab mates and colleagues for their support throughout the years. I would like to thank

Research paper thumbnail of Multi-Task, Multi-Channel, Multi-Input Learning for Mental Illness Detection using Social Media Text

Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)

We investigate the impact of using emotional patterns identified by the clinical practitioners an... more We investigate the impact of using emotional patterns identified by the clinical practitioners and computational linguists to enhance the prediction capabilities of a mental illness detection (in our case depression and posttraumatic stress disorder) model built using a deep neural network architecture. Over the years, deep learning methods have been successfully used in natural language processing tasks, including a few in the domain of mental illness and suicide ideation detection. We illustrate the effectiveness of using multitask learning with a multi-channel convolutional neural network as the shared representation and use additional inputs identified by researchers as indicatives in detecting mental disorders to enhance the model predictability. Given the limited amount of unstructured data available for training, we managed to obtain a task-specific AUC higher than 0.90. In comparison to methods such as multi-class classification, we identified multi-task learning with multi-channel convolution neural network and multiple-inputs to be effective in detecting mental disorders.

Research paper thumbnail of Multi-Task, Multi-Channel, Multi-Input Learning for Mental Illness Detection using Social Media Text

Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)

We investigate the impact of using emotional patterns identified by the clinical practitioners an... more We investigate the impact of using emotional patterns identified by the clinical practitioners and computational linguists to enhance the prediction capabilities of a mental illness detection (in our case depression and posttraumatic stress disorder) model built using a deep neural network architecture. Over the years, deep learning methods have been successfully used in natural language processing tasks, including a few in the domain of mental illness and suicide ideation detection. We illustrate the effectiveness of using multitask learning with a multi-channel convolutional neural network as the shared representation and use additional inputs identified by researchers as indicatives in detecting mental disorders to enhance the model predictability. Given the limited amount of unstructured data available for training, we managed to obtain a task-specific AUC higher than 0.90. In comparison to methods such as multi-class classification, we identified multi-task learning with multi-channel convolution neural network and multiple-inputs to be effective in detecting mental disorders.

Research paper thumbnail of Multi-Task Learning to Capture Changes in Mood Over Time

Proceedings of the Eighth Workshop on Computational Linguistics and Clinical Psychology

Research paper thumbnail of Multi-Task, Multi-Channel, Multi-Input Learning for Mental Illness Detection using Social Media Text

Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019), 2019

We investigate the impact of using emotional patterns identified by the clinical practitioners an... more We investigate the impact of using emotional patterns identified by the clinical practitioners and computational linguists to enhance the prediction capabilities of a mental illness detection (in our case depression and posttraumatic stress disorder) model built using a deep neural network architecture. Over the years, deep learning methods have been successfully used in natural language processing tasks, including a few in the domain of mental illness and suicide ideation detection. We illustrate the effectiveness of using multitask learning with a multi-channel convolutional neural network as the shared representation and use additional inputs identified by researchers as indicatives in detecting mental disorders to enhance the model predictability. Given the limited amount of unstructured data available for training, we managed to obtain a task-specific AUC higher than 0.90. In comparison to methods such as multi-class classification, we identified multi-task learning with multi-channel convolution neural network and multiple-inputs to be effective in detecting mental disorders.

Research paper thumbnail of Mental Illness and Suicide Ideation Detection Using Social Media Data

Mental disorders and suicide have become a global public health problem. Over the years, research... more Mental disorders and suicide have become a global public health problem. Over the years, researchers in computational linguistics have extracted features from social media data for the early detection of users susceptible to mental disorders and suicide ideation. Lack of reliable and inadequate data and the requirement of interpretability can be identified as the principal reasons for the low adoption of neural network architectures in recognizing individuals with mental disorders and suicide ideation. In recent years, a gradual increase in the use of deep neural network architectures in detecting mental disorders and suicide ideation with low false positive and false negative rates became feasible. Our research investigates the efficacy of using a shared representation to learn lower-level features mutual among mental disorders and between mental disorders and suicide ideation. In addition to discovering the shared features between users with suicidal thoughts and users who self-declared a single mental disorder, we further investigate the impact of comorbidities on suicide ideation and use two unseen datasets to investigate the generalizability of the trained models. We use data from two different social media platforms to identify if knowledge can be shared between suicide ideation and mental illness detection tasks across platforms. Through multiple experiments with different but related tasks, we demonstrate the effectiveness of multi-task learning (MTL) when predicting users with mental disorders and suicide my journey to become a researcher and supporting me exceedingly throughout these years. I am incredibly thankful to my kids Thevinshya, Thevinya and Partheeshan, for their understanding of the time and energy I had to contribute throughout the years. I am ever grateful to my mother Turin, my father Piyasena and my sister Chaminie for encouraging my journey in the pursuit of knowledge and my father-in-law Karunagaran and my mother-in-law Nagulambigai for their continuous support. Great thanks to my labmate Ehsan Amjadian for being an amazing friend throughout the years. Through our insightful discussions over the years, I gained a wealth of knowledge about NLP and machine learning. I would like to give my heartful gratitude to all my lab mates and colleagues for their support throughout the years. I would like to thank

Research paper thumbnail of Multi-Task, Multi-Channel, Multi-Input Learning for Mental Illness Detection using Social Media Text

Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)

We investigate the impact of using emotional patterns identified by the clinical practitioners an... more We investigate the impact of using emotional patterns identified by the clinical practitioners and computational linguists to enhance the prediction capabilities of a mental illness detection (in our case depression and posttraumatic stress disorder) model built using a deep neural network architecture. Over the years, deep learning methods have been successfully used in natural language processing tasks, including a few in the domain of mental illness and suicide ideation detection. We illustrate the effectiveness of using multitask learning with a multi-channel convolutional neural network as the shared representation and use additional inputs identified by researchers as indicatives in detecting mental disorders to enhance the model predictability. Given the limited amount of unstructured data available for training, we managed to obtain a task-specific AUC higher than 0.90. In comparison to methods such as multi-class classification, we identified multi-task learning with multi-channel convolution neural network and multiple-inputs to be effective in detecting mental disorders.

Research paper thumbnail of Multi-Task, Multi-Channel, Multi-Input Learning for Mental Illness Detection using Social Media Text

Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)

We investigate the impact of using emotional patterns identified by the clinical practitioners an... more We investigate the impact of using emotional patterns identified by the clinical practitioners and computational linguists to enhance the prediction capabilities of a mental illness detection (in our case depression and posttraumatic stress disorder) model built using a deep neural network architecture. Over the years, deep learning methods have been successfully used in natural language processing tasks, including a few in the domain of mental illness and suicide ideation detection. We illustrate the effectiveness of using multitask learning with a multi-channel convolutional neural network as the shared representation and use additional inputs identified by researchers as indicatives in detecting mental disorders to enhance the model predictability. Given the limited amount of unstructured data available for training, we managed to obtain a task-specific AUC higher than 0.90. In comparison to methods such as multi-class classification, we identified multi-task learning with multi-channel convolution neural network and multiple-inputs to be effective in detecting mental disorders.