Although pain is widely recognized to be a multidimensional experience, it is typically measured by unidimensional patient self-reported visual analog scale (VAS). However, self-reported pain is subjective, difficult to interpret and sometimes impossible to obtain. Machine learning models have been developed to automatically recognize pain at both the frame level and sequence (or video) level. Many methods use or learn facial action units (AUs) defined by the Facial Action Coding System (FACS) for describing facial expressions with muscle movement. In this paper, we analyze the relationship between sequence-level multidimensional pain measurements and frame-level AUs and an AU derived pain-related measure, the Prkachin and Solomon Pain Intensity (PSPI). We study methods that learn sequence-level metrics from frame-level metrics. Specifically, we explore an extended multitask learning model to predict VAS from human-labeled AUs with the help of other sequence-level pain measurements during training. This model consists of two parts: a multitask learning neural network model to predict multidimensional pain scores, and an ensemble learning model to linearly combine the multidimensional pain scores to best approximate VAS. Starting from human-labeled AUs, the model achieves a mean absolute error (MAE) on VAS of 1.73. It outperforms provided human sequence-level estimates which have an MAE of 1.76. Combining our machine learning model with the human estimates gives the best performance of MAE on VAS of 1.48.
more »
« less
Inferring #MeToo Experience Tweets using Classic and Neural Models [Inferring #MeToo Experience Tweets using Classic and Neural Models]
The #MeToo movement is one of several calls for social change to gain traction on Twitter in the past decade. The movement went viral after prominent individuals shared their experiences, and much of its power continues to be derived from experience sharing. Because millions of #MeToo tweets are published every year, it is important to accurately identify experience-related tweets. Therefore, we propose a new learning task and compare the effectiveness of classic machine learning models, ensemble models, and a neural network model that incorporates a pre-trained language model to reduce the impact of feature sparsity. We find that even with limited training data, the neural network model outperforms the classic and ensemble classifiers. Finally, we analyze the experience-related conversation in English during the first year of the #MeToo movement and determine that experience tweets represent a sizable minority of the conversation and are moderately correlated to major events.
more »
« less
- NSF-PAR ID:
- 10351518
- Date Published:
- Journal Name:
- Proceedings of the 11th International Conference on Data Science, Technology and Applications - DATA
- Page Range / eLocation ID:
- 107 to 117
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Effectively filtering and categorizing the large volume of user-generated content on social media during disaster events can help emergency management and disaster response prioritize their resources. Deep learning approaches, including recurrent neural networks and transformer-based models, have been previously used for this purpose. Capsule Neural Networks (CapsNets), initially proposed for image classification, have been proven to be useful for text analysis as well. However, to the best of our knowledge, CapsNets have not been used for classifying crisis-related messages, and have not been extensively compared with state-of-the-art transformer-based models, such as BERT. Therefore, in this study, we performed a thorough comparison between CapsNet models, state-of-the-art BERT models and two popular recurrent neural network models that have been successfully used for tweet classification, specifically, LSTM and Bi-LSTM models, on the task of classifying crisis tweets both in terms of their informativeness (binary classification), as well as their humanitarian content (multi-class classification). For this purpose, we used several benchmark datasets for crisis tweet classification, namely CrisisBench, CrisisNLP and CrisisLex. Experimental results show that the performance of the CapsNet models is on a par with that of LSTM and Bi-LSTM models for all metrics considered, while the performance obtained with BERT models have surpassed the performance of the other three models across different datasets and classes for both classification tasks, and thus BERT could be considered the best overall model for classifying crisis tweets.more » « less
-
Social media has become a powerful and efficient platform for information diffusion. The increasing pervasiveness of social media use, however, has brought about the problems of fraudulent accounts that are intended to diffuse misinformation or malicious contents. Twitter recently released comprehensive archives of fraudulent tweets that are possibly connected to a propaganda effort of Internet Research Agency (IRA) on the 2016 U.S. presidential election. To understand information diffusion in fraudulent networks, we analyze structural properties of the IRA retweet network, and develop deep neural network models to detect fraudulent tweets. The structure analysis reveals key characteristics of the fraudulent network. The experiment results demonstrate the superior performance of the deep learning technique to a traditional classification method in detecting fraudulent tweets. The findings have potential implications for curbing online misinformation.more » « less
-
null (Ed.)Abstract Objective Machine learning is used to understand and track influenza-related content on social media. Because these systems are used at scale, they have the potential to adversely impact the people they are built to help. In this study, we explore the biases of different machine learning methods for the specific task of detecting influenza-related content. We compare the performance of each model on tweets written in Standard American English (SAE) vs African American English (AAE). Materials and Methods Two influenza-related datasets are used to train 3 text classification models (support vector machine, convolutional neural network, bidirectional long short-term memory) with different feature sets. The datasets match real-world scenarios in which there is a large imbalance between SAE and AAE examples. The number of AAE examples for each class ranges from 2% to 5% in both datasets. We also evaluate each model's performance using a balanced dataset via undersampling. Results We find that all of the tested machine learning methods are biased on both datasets. The difference in false positive rates between SAE and AAE examples ranges from 0.01 to 0.35. The difference in the false negative rates ranges from 0.01 to 0.23. We also find that the neural network methods generally has more unfair results than the linear support vector machine on the chosen datasets. Conclusions The models that result in the most unfair predictions may vary from dataset to dataset. Practitioners should be aware of the potential harms related to applying machine learning to health-related social media data. At a minimum, we recommend evaluating fairness along with traditional evaluation metrics.more » « less
-
Abstract The process of evapotranspiration transfers liquid water from vegetation and soil surfaces to the atmosphere, the so-called latent heat flux ( Q LE ), and modulates the Earth’s energy, water, and carbon cycle. Vegetation controls Q LE by regulating leaf stomata opening (surface resistance r s in the Big Leaf approach) and by altering surface roughness (aerodynamic resistance r a ). Estimating r s and r a across different vegetation types is a key challenge in predicting Q LE . We propose a hybrid approach that combines mechanistic modeling and machine learning for modeling Q LE . The hybrid model combines a feed-forward neural network which estimates the resistances from observations as intermediate variables and a mechanistic model in an end-to-end setting. In the hybrid modeling setup, we make use of the Penman–Monteith equation in conjunction with multi-year flux measurements across different forest and grassland sites from the FLUXNET database. This hybrid model setup is successful in predicting Q LE , however, this approach leads to equifinal solutions in terms of estimated physical parameters. We follow two different strategies to constrain the hybrid model and therefore control for the equifinality that arises when the two resistances are estimated simultaneously. One strategy is to impose an a priori constraint on r a based on mechanistic assumptions (theory-driven strategy), while the other strategy makes use of more observational data and adds a constraint in predicting r a through multi-task learning of both latent and sensible heat flux ( Q H ; data-driven strategy) together. Our results show that all hybrid models predict the target variables with a high degree of success, with R 2 = 0.82–0.89 for grasslands and R 2 = 0.70–0.80 for forest sites at the mean diurnal scale. The predicted r s and r a show strong physical consistency across the two regularized hybrid models, but are physically implausible in the under-constrained hybrid model. The hybrid models are robust in reproducing consistent results for energy fluxes and resistances across different scales (diurnal, seasonal, and interannual), reflecting their ability to learn the physical dependence of the target variables on the meteorological inputs. As a next step, we propose to test these heavily observation-informed parameterizations derived through hybrid modeling as a substitute for ad hoc formulations in Earth system models.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.5220/0011278100003269
