We propose a deep learning architecture and test three other machine learning models to automatically detect individuals that will attempt suicide within (1) 30 days and (2) six months, using their social media post data provided in (Macavaney et al., 2021) via the CLPsych 2021 shared task. 

Additionally, we create and extract three sets of handcrafted features for suicide risk detection based on the three-stage theory of suicide and prior work on emotions and the use of pronouns among persons exhibiting suicidal ideations. 

Extensive experimentations show that some of the traditional machine learning methods outperform the baseline with an F1 score of 0.741 and F2 score of 0.833 on subtask 1 (prediction of a suicide attempt 30 days prior). However, the proposed deep learning method outperforms the baseline with F1 score of 0.737 and F2 score of 0.843 on subtask 2 (prediction of suicide 6 months prior).

More Details

Rumor (Fake News) identification is a very critical task with significant implications to economy, democracy as well as public health and safety. 

We tackle the problem of automated detection of rumors in social media in this work by designing a modular explainable architecture that uses both latent and handcrafted features and can be expanded to as many new classes of features as desired. 

This approach allows the end user to not only determine whether the piece of information on the social media is real of a rumor, but also give explanations on why the algorithm arrived at its conclusion. 

In this work, we propose three explainable deep learning architectures to automatically detect patients with Alzheimer's disease based on their language abilities. The architectures use: (1) only the part-of-speech features; (2) only language embedding features and (3) both of these feature classes via a unified architecture, respectively. 

We use self-attention mechanisms and interpretable 1-dimensional ConvolutionalNeural Network (CNN) to generate two types of explanations of the model's action: intra-class explanation and inter-class explanation. 

Extensive experimentation and comparison with several recent models show that our method outperforms these methods with an accuracy of 92.2% and F1 score of 0.952 on the DementiaBank dataset while being able to generate explanations. 

Alzheimers disease (AD)-related global healthcare cost is estimated to be $1 trillion by 2050. Currently, there is no cure for this disease; however, clinical studies show that early diagnosis and intervention helps to extend the quality of life and inform technologies for personalized mental healthcare. Clinical research indicates that the onset and progression of Alzheimers disease lead to dementia and other mental health issues. As a result, the language capabilities of patient start to decline. In this paper, we show that machine learning-based unsupervised clustering of and anomaly detection with linguistic biomarkers are promising approaches for intuitive visualization and personalized early stage detection of Alzheimers disease. We demonstrate this approach on 10 years (1980 to 1989) of President Ronald Reagans speech data set. Key linguistic biomarkers that indicate early-stage AD are identified. Experimental results show that Reagan had early onset of Alzheimers sometime between 1983 and 1987. This finding is corroborated by prior work that analyzed his interviews using a statistical technique. The proposed technique also identifies the exact speeches that reflect linguistic biomarkers for early stage AD.

We address the problem of estimating the source of a rumor in large-scale social networks. 

Internode relationship strengths in real social networks are random. We model this uncertainty by using random, non-homogenous edge weights on the underlying social network graph. We propose a novel two-stage algorithm that uses the modularity of the social network to locate the source of the rumor with fewer sensor nodes than other existing algorithms. We also propose a novel method to select these sensor nodes. 

We evaluate our algorithm using a large data set from Twitter and Sina Weibo. Real-world time series data are used to model the uncertainty in social relationship strengths. Simulations show that the proposed algorithm can determine the actual source within two hops, 69%-80% of the time, when the diameter of the networks varies between 7 and 13. 

Details coming soon...

Details coming soon...

Details coming soon...