Personality computing has become an emerging topic in computer vision, due to the wide range of applications it can be used for. However, most works on the topic have focused on analyzing the individual, even when applied to interaction scenarios, and for short periods of time. To address these limitations, we present the Dyadformer, a novel multi-modal multi-subject Transformer architecture to model individual and interpersonal features in dyadic interactions using variable time windows, thus allowing the capture of long-term interdependencies. Our proposed cross-subject layer allows the network to explicitly model interactions among subjects through attentional operations. This proof-of-concept approach shows how multi-modality and joint modeling of both interactants for longer periods of time helps to predict individual attributes. With Dyadformer, we improve state-of-the-art self-reported personality inference results on individual subjects on the UDIVA v0.5 dataset.
Our research focuses on studying and developing methods for reducing the dimensionality of large datasets, common in biomedical applications. A major problem when learning information about patients based on genetic sequencing data is that there are often more feature variables (genetic data) than observations (patients). This makes direct supervised learning difficult. One way of reducing the feature space is to use latent Dirichlet allocation in order to group genetic variants in an unsupervised manner. Latent Dirichlet allocation is a common model in natural language processing, which describes a document as a mixture of topics, each with a probability of generating certain words. This can be generalized as a Bayesian tensor decomposition to account for multiple feature variables. While we made some progress improving and modifying these methods, our significant contributions are with hierarchical topic modeling. We developed distinct methods of incorporating hierarchical topic modeling, based on nested Chinese restaurant processes and Pachinko Allocation Machine, into Bayesian tensor decompositions. We apply these models to predict whether or not patients have autism spectrum disorder based on genetic sequencing data. We examine a dataset from National Database for Autism Research consisting of paired siblings -- one with autism, and the other without -- and counts of their genetic variants. Additionally, we linked the genes with their Reactome biological pathways. We combine this information into a tensor of patients, counts of their genetic variants, and the membership of these genes in pathways. Once we decompose this tensor, we use logistic regression on the reduced features in order to predict if patients have autism. We also perform a similar analysis of a dataset of patients with one of four common types of cancer (breast, lung, prostate, and colorectal).
This paper employs two major natural language processing techniques, topic modeling and clustering, to find patterns in folktales and reveal cultural relationships between regions. In particular, we used Latent Dirichlet Allocation and BERTopic to extract the recurring elements as well as K-means clustering to group folktales. Our paper tries to answer the question what are the similarities and differences between folktales, and what do they say about culture. Here we show that the common trends between folktales are family, food, traditional gender roles, mythological figures, and animals. Also, folktales topics differ based on geographical location with folktales found in different regions having different animals and environment. We were not surprised to find that religious figures and animals are some of the common topics in all cultures. However, we were surprised that European and Asian folktales were often paired together. Our results demonstrate the prevalence of certain elements in cultures across the world. We anticipate our work to be a resource to future research of folktales and an example of using natural language processing to analyze documents in specific domains. Furthermore, since we only analyzed the documents based on their topics, more work could be done in analyzing the structure, sentiment, and the characters of these folktales.
Human language, the most powerful communication system in history, is closely associated with cognition. Written text is one of the fundamental manifestations of language, and the study of its universal regularities can give clues about how our brains process information and how we, as a society, organize and share it. Still, only classical patterns such as Zipf's law have been explored in depth. In contrast, other basic properties like the existence of bursts of rare words in specific documents, the topical organization of collections, or the sublinear growth of vocabulary size with the length of a document, have only been studied one by one and mainly applying heuristic methodologies rather than basic principles and general mechanisms. As a consequence, there is a lack of understanding of linguistic processes as complex emergent phenomena. Beyond Zipf's law for word frequencies, here we focus on Heaps' law, burstiness, and the topicality of document collections, which encode correlations within and across documents absent in random null models. We introduce and validate a generative model that explains the simultaneous emergence of all these patterns from simple rules. As a result, we find a connection between the bursty nature of rare words and the topical organization of texts and identify dynamic word ranking and memory across documents as key mechanisms explaining the non trivial organization of written text. Our research can have broad implications and practical applications in computer science, cognitive science, and linguistics.
Since most machine learning models provide no explanations for the predictions, their predictions are obscure for the human. The ability to explain a model's prediction has become a necessity in many applications including Twitter mining. In this work, we propose a method called Explainable Twitter Mining (Ex-Twit) combining Topic Modeling and Local Interpretable Model-agnostic Explanation (LIME) to predict the topic and explain the model predictions. We demonstrate the effectiveness of Ex-Twit on Twitter health-related data.
Parallel to the rising debates over sustainable energy and artificial intelligence solutions, the world is currently discussing the ethics of artificial intelligence and its possible negative effects on society and the environment. In these arguments, sustainable AI is proposed, which aims at advancing the pathway toward sustainability, such as sustainable energy. In this paper, we offered a novel contextual topic modeling combining LDA, BERT, and Clustering. We then combined these computational analyses with content analysis of related scientific publications to identify the main scholarly topics, sub-themes, and cross-topic themes within scientific research on sustainable AI in energy. Our research identified eight dominant topics including sustainable buildings, AI-based DSSs for urban water management, climate artificial intelligence, Agriculture 4, the convergence of AI with IoT, AI-based evaluation of renewable technologies, smart campus and engineering education, and AI-based optimization. We then recommended 14 potential future research strands based on the observed theoretical gaps. Theoretically, this analysis contributes to the existing literature on sustainable AI and sustainable energy, and practically, it intends to act as a general guide for energy engineers and scientists, AI scientists, and social scientists to widen their knowledge of sustainability in AI and energy convergence research.
In many applications of time series models, such as climate analysis and social media analysis, we are often interested in extreme events, such as heatwave, wind gust, and burst of topics. These time series data usually exhibit a heavy-tailed distribution rather than a Gaussian distribution. This poses great challenges to existing approaches due to the significantly different assumptions on the data distributions and the lack of sufficient past data on extreme events. In this paper, we propose the Sparse-GEV model, a latent state model based on the theory of extreme value modeling to automatically learn sparse temporal dependence and make predictions. Our model is theoretically significant because it is among the first models to learn sparse temporal dependencies among multivariate extreme value time series. We demonstrate the superior performance of our algorithm to the state-of-art methods, including Granger causality, copula approach, and transfer entropy, on one synthetic dataset, one climate dataset and two Twitter datasets.
With the information explosion of news articles, personalized news recommendation has become important for users to quickly find news that they are interested in. Existing methods on news recommendation mainly include collaborative filtering methods which rely on direct user-item interactions and content based methods which characterize the content of user reading history. Although these methods have achieved good performances, they still suffer from data sparse problem, since most of them fail to extensively exploit high-order structure information (similar users tend to read similar news articles) in news recommendation systems. In this paper, we propose to build a heterogeneous graph to explicitly model the interactions among users, news and latent topics. The incorporated topic information would help indicate a user's interest and alleviate the sparsity of user-item interactions. Then we take advantage of graph neural networks to learn user and news representations that encode high-order structure information by propagating embeddings over the graph. The learned user embeddings with complete historic user clicks capture the users' long-term interests. We also consider a user's short-term interest using the recent reading history with an attention based LSTM model. Experimental results on real-world datasets show that our proposed model significantly outperforms state-of-the-art methods on news recommendation.