More Like this

1. A machine learning‐based analysis of 311 requests in the Miami‐Dade County

   https://doi.org/10.1111/grow.12578  

   Cheng, Shaoming; Ganapati, Sukumar; Narasimhan, Giri; Yusuf, Farzana Beente (September 2021, Growth and Change)

   Carruthers, John; Duncan, Natasha; He, Canfei; Zhu, Shengjun (Ed.)

   This paper illustrates the application of machine learning algorithms in predictive analytics for local governments using administrative data. The developed and tested machine learning predictive algorithm overcomes known limitations of the conventional ordinary least squares method. Such limitations include but not limited to imposed linearity, presumed causality with independent variables as presumed causes and dependent variables as presume result, likely high multicollinearity among features, and spatial autocorrelation. The study applies the algorithms to 311 non-emergency service requests in the context of Miami-Dade County. The algorithms are applied to predict the volume of 311 service requests and the community characteristics affecting the volume across Census tract neighborhoods. Four common families of algorithms and an ensemble of them are applied. They are random forest, support vector machines, lasso and elastic-net regularized generalized linear models, and extreme gradient boosting. Two feature selection methods, namely Boruta and fscaret, are applied to identify the significant community characteristics. The results show that the machine learning algorithms capture spatial autocorrelation and clustering. The features generated by fscaret algorithms are parsimonious in predicting the 311 service request volume. 

   more » « less
2. Integrating Multimodal Information in Large Pretrained Transformers

   Rahman, Wasifur; Hasan, Md Kamrul; Lee, Sangwu; Zadeh, AmirAli Bagher; Mao, Chengfeng; Morency, Louis-Philippe; Hoque, Ehsan (January 2020, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics)

   Recent Transformer-based contextual word representations, including BERT and XLNet, have shown state-of-the-art performance in multiple disciplines within NLP. Fine-tuning the trained contextual models on task-specific datasets has been the key to achieving superior performance downstream. While fine-tuning these pre-trained models is straightforward for lexical applications (applications with only language modality), it is not trivial for multimodal language (a growing area in NLP focused on modeling face-to-face communication). More specifically, this is due to the fact that pre-trained models don’t have the necessary components to accept two extra modalities of vision and acoustic. In this paper, we proposed an attachment to BERT and XLNet called Multimodal Adaptation Gate (MAG). MAG allows BERT and XLNet to accept multimodal nonverbal data during fine-tuning. It does so by generating a shift to internal representation of BERT and XLNet; a shift that is conditioned on the visual and acoustic modalities. In our experiments, we study the commonly used CMU-MOSI and CMU-MOSEI datasets for multimodal sentiment analysis. Fine-tuning MAG-BERT and MAG-XLNet significantly boosts the sentiment analysis performance over previous baselines as well as language-only fine-tuning of BERT and XLNet. On the CMU-MOSI dataset, MAG-XLNet achieves human-level multimodal sentiment analysis performance for the first time in the NLP community. 

   more » « less
3. A Data Envelopment Analysis-based Approach for Managing Performance of Public Service Systems During a Disaster

   Pamukcu, Duygu; Zobel, Christopher; Ge, Yue (January 2022, Proceedings of the 19th ISCRAM Conference)

   In addition to their normal task of supporting community participation, engagement, and improved information access, information technology-based public service systems are also essential for maintaining critical services and providing effective communication with citizens before, during, and after emergencies. This study focuses on the impacts of disaster events on the operational performance of such service systems and discusses opportunities for managing service efficiency by rearranging and reallocating resources during emergencies. To the best of our knowledge, this is the first attempt to provide a practical method for improving the relative efficiency of public service systems in such a context. We suggest a Data Envelopment Analysis (DEA) approach for quantifying the relative efficiencies associated with service requests from an input-output-based standpoint, and discuss the Orange County (Florida) 311 non-emergency service system, in the context of the COVID-19 pandemic, as an example of how such operational efficiency can be managed during a disruption. 

   more » « less
4. Can Cash Incentives Reduce Syringe Litter? Evidence From Boston's 311 Service Requests

   https://doi.org/10.1111/psj.70063  

   Le, Angie N; Zhao, Boyuan; Cheng, Shaoming; Ganapati, Sukumar (July 2025, Policy Studies Journal)

   ABSTRACT Syringe littering in public places is a public health problem in many big cities nationwide amid the ongoing opioid crisis. Besides needle exchanges and/or safe disposal efforts, cash incentives have come into play as a policy tool to address the issue. In December 2020, the City of Boston launched the Community Syringe Redemption Program (CSRP), which offers a nominal cash “buy back” incentive for used syringes at designated centers. This study examines the impact of Boston's CSRP on reducing syringe litter. It employs a distance band‐based, near‐far identification strategy and uses the difference‐in‐differences (DID) to analyze Boston's 311 service requests related to needle pickup and the number of discarded needles discovered in response to the pickup requests before and after CSRP's implementation. Results show that both 311 requests and publicly discarded syringes have reduced significantly in neighborhoods located within a 0.5‐mile radius of the CSRP redemption center. There are no statistically significant reductions observed in 0.5–1‐mile or 1–1.5‐mile donut bands around the center. In effect, although CSRP could be effective in reducing syringe littering, its impact is geographically bounded and sensitive to the redemption centers' locations. Results from alternative models, robustness tests, and placebo tests are consistent with main findings. 

   more » « less
5. Strategies for Crisis-Responsive Governance: Automated Anomaly Identification in Public Services

   Unveren, H; Lehyeh, AA; Pamukcu, D; Zobel, CW (May 2024, https://ojs.iscram.org/index.php/Proceedings)

   Penkert, B; Hellingrath, B; Rode, M; Widera, A; Middelhoff, M; Boersma, K; Kalthoner, M (Ed.)

   This paper introduces a machine learning tool for service systems, focusing on accurate classification of service requests and swift anomaly detection, particularly crucial during emergencies. Employing a Support Vector Machine model, this tool automatically classifies service calls into predefined categories with high accuracy, while effectively detecting irregular requests that require specific attention from operators. This approach streamlines resource management by reducing the manuaI categorization workload and enables early detection of emerging service needs. Examining Orange County, Florida 311 System data, with a specific focus on the COVID-19 period, we illustrate the tool's success in automatic request categorization and anomaly detection. Overall, this tool presents an effective automation approach to help with efficient resource management of service systems and proactive assessment of public service needs, promising to revolutionize service request management during crises. Future work will explore additional classification models for enhanced accuracy and integrate automated alerts for proactive disaster management. 

   more » « less