Foodborne diseases and outbreaks are significant threats to public health, resulting in millions of illnesses and deaths worldwide each year. Traditional foodborne disease surveillance systems rely on data from healthcare facilities, laboratories, and government agencies to monitor and control outbreaks. Recently, there is a growing recognition of the potential value of incorporating social media data into surveillance systems. This paper explores the use of social media data as an alternative surveillance tool for foodborne diseases by collecting large-scale Twitter data, building food safety data storage models, and developing a novel frontend foodborne illness surveillance system. Descriptive and predictive analyses of the collected data were conducted in comparison with ground truth data reported by the U.S. Centers for Disease Control and Prevention (CDC). The results indicate that the most implicated food categories and the distributions from both Twitter and the CDC were similar. The system developed with Twitter data could complement traditional foodborne disease surveillance systems by providing near-real-time information on foodborne illnesses, implicated foods, symptoms, locations, and other information critical for detecting a potential foodborne outbreak.

Sequential tabular data is one of the most commonly used data types in real-world applications. Different from conventional tabular data, where rows in a table are independent, sequential tabular data contains rich contextual and sequential information, where some fields aredynamically changing over time and others arestatic. Existing transformer-based approaches analyzing sequential tabular data overlook the differences between dynamic and static fields by replicating and filling static fields into each record, and ignore temporal information between rows, which leads to three major disadvantages: (1) computational overhead, (2) artificially simplified data for masked language modeling pre-training task that may yield less meaningful representations, and (3) disregarding the temporal behavioral patterns implied by time intervals. In this work, we propose FATA-Trans, a model with two field transformers for modeling sequential tabular data, where each processes static and dynamic field information separately. FATA-Trans isfield - andtime -aware for sequential tabular data. Thefield -type embedding in the method enables FATA-Trans to capture differences between static and dynamic fields. Thetime -aware position embedding exploits both order and time interval information between rows, which helps the model detect underlying temporal behavior in a sequence. Our experiments on three benchmark datasets demonstrate that the learned representations from FATA-Trans consistently outperform state-of-the-art solutions in the downstream tasks. We also present visualization studies to highlight the insights captured by the learned representations, enhancing our understanding of the underlying data. Our codes are available at https://github.com/zdy93/FATA-Trans.

Diseases caused by the consumption of food are a significant but avoidable public health issue, and identifying the source of contamination is a key step in an outbreak investigation to prevent foodborne illnesses. Historical foodborne outbreaks provide rich data on critical attributes such as outbreak factors, food vehicles, and etiologies, and an improved understanding of the relationships between these attributes could provide insights for developing effective food safety interventions. The purpose of this study was to identify hidden patterns underlying the relations between the critical attributes involved in historical foodborne outbreaks through data mining approaches. A statistical analysis was used to identify the associations between outbreak factors and food sources, and the factors that were strongly significant were selected as predictive factors for food vehicles. A multinomial prediction model was built based on factors selected for predicting “simple” foods (beef, dairy, and vegetables) as sources of outbreaks. In addition, the relations between the food vehicles and common etiologies were investigated through text mining approaches (support vector machines, logistic regression, random forest, and naïve Bayes). A support vector machine model was identified as the optimal model to predict etiologies from the occurrence of food vehicles. Association rules also indicated the specific food vehicles that have strong relations to the etiologies. Meanwhile, a food ingredient network describing the relationships between foods and ingredients was constructed and used with Monte Carlo simulation to predict possible ingredients from foods that cause an outbreak. The simulated results were confirmed with foods and ingredients that are already known to cause historical foodborne outbreaks. The method could provide insights into the prediction of the possible ingredient sources of contamination when given the name of a food. The results could provide insights into the early identification of food sources of contamination and assist in future outbreak investigations. The data-driven approach will provide a new perspective and strategies for discovering hidden knowledge from massive data.

The extraction of knowledge about the prevalent issues discussed on social media in Africa using Artificial Intelligence techniques is vital for informing public governance. The goals of our study are twofold: (a) to develop machine learning-based models to identify common topics of social concern about Africa on social media, and (b) to design a classifier capable of inferring a particular common topic associated with a given social media post.We designed a three-step framework to achieve the former goal, namely, topic identification. The first step uses text-based representation learning methods to generate text embeddings for feature representation. The second step leverages state-of-the-art Natural Language Processing models, commonly called topic modeling, to organize the representations into groups. The third step generates topics from each group, including by means of using large language models to generate meaningful short-sentence labels from the bag-of-tokens associated with each group. Furthermore, we use Llama2 to deduce the words into a single word theme that describes each topic in relation to social concerns about development. To achieve the second goal of classification; we trained classifiers using ensemble voting and stacking learners to infer which among the identified common topics best characterizes the social media post. For our experimental study, we collected a text corpus called Social Media for Africa composed of 22,036 records extracted from social media comments on Twitter (X) and YouTube. The clustering-based model BERTopic yielded 304 topics, at topic coherence 0.81 C-v. On merging the topics into classes, the BERTopic+ created 11 common topic classes at topic coherence 0.76 C-v. For theme extraction, we additionally refined the leading token words with Llama2 to generate concise single-word theme labels, resulting in 98 unique themes by BERTopic_theme with a C-v score of 0.75 and an IRBO score of 0.50.We then utilized the identified topics based on the resulting groupings as labels for training a topic classifier. These labels were created using Llama2 on our SMA corpus. Our comparative study of topic classifiers using stacking and voting schemes shows that the BERTopic model features 0.83 accuracy and 0.82 F1 score with ensemble voting for training on topics. Furthermore, training on topic classes, BERTopic+ with ensemble voting had the highest accuracy of 0.95 and F1 score of 0.95 compared to other alternate methods on our corpus. The BERTopic_theme also achieved higher performance with ensemble voting classifier at 0.93 F1 score and accuracy 0.93. The overall performance of classifiers using the ensemble stacking is slightly better than that of voting methods for short sentence topic labeling. For Africa, policymakers should focus on the most pressing social issues: COVID-19 restrictions affecting public health and economic recovery, promoting entrepreneurial innovation in energy and environmental sustainability to combat climate change, and strategically responding to China’s rise in global politics to maintain geopolitical stability and foster international cooperation.

Foodborne illness is a serious but preventable public health problem -- with delays in detecting the associated outbreaks resulting in productivity loss, expensive recalls, public safety hazards, and even loss of life. While social media is a promising source for identifying unreported foodborne illnesses, there is a dearth of labeled datasets for developing effective outbreak detection models. To accelerate the development of machine learning-based models for foodborne outbreak detection, we thus present TWEET-FID (TWEET-Foodborne Illness Detection), the first publicly available annotated dataset for multiple foodborne illness incident detection tasks. TWEET-FID collected from Twitter is annotated with three facets: tweet class, entity type, and slot type, with labels produced by experts as well as by crowdsource workers. We introduce several domain tasks leveraging these three facets: text relevance classification (TRC), entity mention detection (EMD), and slot filling (SF). We describe the end-to-end methodology for dataset design, creation, and labeling for supporting model development for these tasks. A comprehensive set of results for these tasks leveraging state-of-the-art single- and multi-task deep learning methods on the TWEET-FID dataset are provided. This dataset opens opportunities for future research in foodborne outbreak detection.