Augmenting Semantic Representation of Depressive Language: From Forums to Microblogs

Farruque, Nawshad; Zaı̈ane, Osmar R.; Goebel, Randy

doi:10.1007/978-3-030-46133-1_22

Cited by 8 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the authors have used the CNN model to learn high-quality features, their method does not consider temporal dynamics coupled with latent topics, which we show to play a crucial role in overall quantitative performance. Farruque et al, [16] study the problem of creating word embeddings in cases where the data is scarce, for instance, depressive language detection from user tweets. The underlying motivation of their work is to simulate a retrofitting-based word embedding approach [17] where they begin with a pre-trained model and fine-tune the model on domain-specific data.…”

Section: User-level Behavioursmentioning

confidence: 99%

Explainable depression detection with multi-aspect features using a hybrid deep learning model on social media

et al. 2022

View full text Add to dashboard Cite

The ability to explain why the model produced results in such a way is an important problem, especially in the medical domain. Model explainability is important for building trust by providing insight into the model prediction. However, most existing machine learning methods provide no explainability, which is worrying. For instance, in the task of automatic depression prediction, most machine learning models lead to predictions that are obscure to humans. In this work, we propose explainable Multi-Aspect Depression Detection with Hierarchical Attention Network MDHAN, for automatic detection of depressed users on social media and explain the model prediction. We have considered user posts augmented with additional features from Twitter. Specifically, we encode user posts using two levels of attention mechanisms applied at the tweet-level and word-level, calculate each tweet and words’ importance, and capture semantic sequence features from the user timelines (posts). Our hierarchical attention model is developed in such a way that it can capture patterns that leads to explainable results. Our experiments show that MDHAN outperforms several popular and robust baseline methods, demonstrating the effectiveness of combining deep learning with multi-aspect features. We also show that our model helps improve predictive performance when detecting depression in users who are posting messages publicly on social media. MDHAN achieves excellent performance and ensures adequate evidence to explain the prediction.

show abstract

Section: User-level Behavioursmentioning

confidence: 99%

Explainable depression detection with multi-aspect features using a hybrid deep learning model on social media

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Word-Embedding-Family(WEF) We use several classic word embedding models, including Google News (Google) 4 , Twitter Glove (Glove) 5 , Twitter Skip-gram Embedding (TE) [10], Depression Specific Embedding (DSE) trained on Depression specific corpora [9], Depression Embedding Augmented Twitter Embedding (ATE) [9], NLI pre-trained Roberta Embedding (Roberta-NLI) [15] and Universal Sentence Encoder Embedding (USE) [4]. All these embeddings except DSE have been trained on millions of tokens.…”

Section: Representation Of Tweets and Labels For Zslmentioning

confidence: 99%

“…Word Vector Mapper Models(WV-MAPPER) As originally proposed in [9], we learn a least square projection matrix, M w , between the word vectors of the common vocabulary V of both source and target embeddings. This learned matrix is then used to adjust word vectors of source embedding, then later used to build WV-AVG sentence representation as outlined in Equation 1.…”

Section: Representation Of Tweets and Labels For Zslmentioning

confidence: 99%

“…This learned matrix is then used to adjust word vectors of source embedding, then later used to build WV-AVG sentence representation as outlined in Equation 1. This method has been previously found to be effective for the depressive post detection task [9]. For our WV-MAPPER models, our source embedding is one of the general Twitter pre-trained embedding (TE) and the target is the Depression Specific Embedding (DSE).…”

Section: Representation Of Tweets and Labels For Zslmentioning

confidence: 99%

See 1 more Smart Citation

STEP-EZ: Syntax Tree guided semantic ExPlanation for Explainable Zero-shot modeling of clinical depression symptoms from text

Farruque,

Goebel,

Zaiane

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We focus on exploring various approaches of Zero-Shot Learning (ZSL) and their explainability for a challenging yet important supervised learning task notorious for training data scarcity, i.e. Depression Symptoms Detection (DSD) from text. We start with a comprehensive synthesis of different components of our ZSL modeling and analysis of our ground truth samples and Depression symptom clues curation process with the help of a practicing clinician. We next analyze the accuracy of various state-of-the-art ZSL models and their potential enhancements for our task. Further, we sketch a framework for the use of ZSL for hierarchical text-based explanation mechanism, which we call, Syntax Tree-Guided Semantic Explanation (STEP). Finally, we summarize experiments from which we conclude that we can use ZSL models and achieve reasonable accuracy and explainability, measured by a proposed Explainability Index (EI). This work is, to our knowledge, the first work to exhaustively explore the efficacy of ZSL models for DSD task, both in terms of accuracy and explainability.

show abstract

“…Farruque et al, [13] study the problem of creating word embeddings in cases where the data is scarce, for instance, depressive language detection from user tweets. The underlying motivation of their work is to simulate a retrofitting-based word embedding approach [14] where they begin with a pre-trained model and fine-tune the model on domain-specific data.…”

Section: Word Embeddings For Depression Detectionmentioning

confidence: 99%

Explainable Depression Detection with Multi-Modalities Using a Hybrid Deep Learning Model on Social Media

Zogan,

Razzak,

Wang

et al. 2020

Preprint

View full text Add to dashboard Cite

Social networks enable people to interact with one another by sharing information, sending messages, making friends, and having discussions, which generates massive amounts of data every day, popularly called as the user-generated content. This data is present in various forms such as images, text, videos, links, and others and reflects user behaviours including their mental states. It is challenging yet promising to automatically detect mental health problems from such data which is short, sparse and sometimes poorly phrased. However, there are efforts to automatically learn patterns using computational models on such user-generated content. While many previous works have largely studied the problem on a small-scale by assuming uni-modality of data which may not give us faithful results, we propose a novel scalable hybrid model that combines Bidirectional Gated Recurrent Units (BiGRUs) and Convolutional Neural Networks to detect depressed users on social media such as Twitter-based on multi-modal features. Specifically, we encode words in user posts using pre-trained word embeddings and BiGRUs to capture latent behavioural patterns, long-term dependencies, and correlation across the modalities, including semantic sequence features from the user timelines (posts). The CNN model then helps learn useful features. Our experiments show that our model outperforms several popular and strong baseline methods, demonstrating the effectiveness of combining deep learning with multi-modal features. We also show that our model helps improve predictive performance when detecting depression in users who are posting messages publicly on social media.

show abstract

Augmenting Semantic Representation of Depressive Language: From Forums to Microblogs

Cited by 8 publications

References 31 publications

Explainable depression detection with multi-aspect features using a hybrid deep learning model on social media

Explainable depression detection with multi-aspect features using a hybrid deep learning model on social media

STEP-EZ: Syntax Tree guided semantic ExPlanation for Explainable Zero-shot modeling of clinical depression symptoms from text

Explainable Depression Detection with Multi-Modalities Using a Hybrid Deep Learning Model on Social Media

Contact Info

Product

Resources

About