Massimo Pacella
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Massimo Pacella has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Gabriele Papadia
Department of Engineering for Innovation, University of Salento, 73100 Lecce, Italy
12 shared publications - Quirico Semeraro
Dipartimento di Meccanica, Politecnico di Milano, Milan, Italy
9 shared publications - Bianca Maria Colosimo
Dipartimento di Meccanica, Politecnico di Milano, Milan, Italy
8 shared publications - Alfredo Anglani
Università del Salento
6 shared publications - Vincenzo Giliberti
IN & OUT S.p.A. a Socio Unico Teleperformance S.E., 74121 Taranto, Italy
5 shared publications - Antonio Papa
Department of Science and Information Technology, Pegaso University, 80121 Napoli, Italy
3 shared publications
Latest Publications
- Open Access
- 27 July 2026
- Published by MDPI AG in Algorithms
- Vol. 19 (8) , 627
Governed Agentic Process Automation: A Floor-Safety Guarantee for Compliance-Critical LLM Routing
Agentic Process Automation (APA) extends Robotic Process Automation by delegating workflow construction and runtime decisions to Large Language Model (LLM) agents. In regulated business processes, this autonomy creates a specific safety risk: an LLM may recognize elevated risk while still failing to trigger the human approval required by policy. We propose Governed APA, a runtime decision architecture that bounds LLM autonomy through schema-validated inputs, a closed action space, a policy-derived floor guardrail, and a deterministic fallback. We formalize the governed decision and establish a floor-safety property ensuring that the executed action cannot under-escalate below the policy-mandated minimum. The architecture is evaluated on a structured employee-onboarding case study with 166 profiles and explicit human-in-the-loop (HITL) ground truth. We compare a deterministic baseline, an ungoverned LLM, and a guarded LLM using two local models, Qwen2.5 and llama3.1. Ungoverned Qwen2.5 identified elevated risk but failed to escalate any of the 43 sensitive cases to mandatory human approval, yielding HITL recall equal to 0. Ungoverned llama3.1 showed the opposite failure mode, achieving full recall but producing unnecessary human-approval escalations. With the floor guardrail active, Qwen2.5 HITL recall increased to 1.0, llama3.1 recall remained 1.0, and inter-run stability of the compliance decision increased from 0.73 to 1.0 for Qwen2.5. On this dataset and configuration, no false-positive HITL escalation was introduced for Qwen2.5. These results show that compliance-critical APA requires architectural governance rather than prompt-level reliance on LLM discretion. The policy-derived floor guardrail enforces the floor-safety property and prevents silent under-escalation. The guarantee is local: it constrains the compliance routing decision under validated inputs and a trusted policy, and does not cover input corruption, policy errors, extraction failures, prompt injection, downstream tool misuse, or end-to-end workflow correctness. The evaluation is a single-process, two-model proof of concept, and generalization to other regulated workflows is a hypothesis for future validation.
- 27 July 2026
- Published by MDPI AG in Algorithms
- Vol. 19 (8) , 627
Open AccessGoverned Agentic Process Automation: A Floor-Safety Guarantee for Compliance-Critical LLM Routing
Agentic Process Automation (APA) extends Robotic Process Automation by delegating workflow construction and runtime decisions to Large Language Model (LLM) agents. In regulated business processes, this autonomy creates a specific safety risk: an LLM may recognize elevated risk while still failing to trigger the human approval required by policy. We propose Governed APA, a runtime decision architecture that bounds LLM autonomy through schema-validated inputs, a closed action space, a policy-derived floor guardrail, and a deterministic fallback. We formalize the governed decision and establish a floor-safety property ensuring that the executed action cannot under-escalate below the policy-mandated minimum. The architecture is evaluated on a structured employee-onboarding case study with 166 profiles and explicit human-in-the-loop (HITL) ground truth. We compare a deterministic baseline, an ungoverned LLM, and a guarded LLM using two local models, Qwen2.5 and llama3.1. Ungoverned Qwen2.5 identified elevated risk but failed to escalate any of the 43 sensitive cases to mandatory human approval, yielding HITL recall equal to 0. Ungoverned llama3.1 showed the opposite failure mode, achieving full recall but producing unnecessary human-approval escalations. With the floor guardrail active, Qwen2.5 HITL recall increased to 1.0, llama3.1 recall remained 1.0, and inter-run stability of the compliance decision increased from 0.73 to 1.0 for Qwen2.5. On this dataset and configuration, no false-positive HITL escalation was introduced for Qwen2.5. These results show that compliance-critical APA requires architectural governance rather than prompt-level reliance on LLM discretion. The policy-derived floor guardrail enforces the floor-safety property and prevents silent under-escalation. The guarantee is local: it constrains the compliance routing decision under validated inputs and a trusted policy, and does not cover input corruption, policy errors, extraction failures, prompt injection, downstream tool misuse, or end-to-end workflow correctness. The evaluation is a single-process, two-model proof of concept, and generalization to other regulated workflows is a hypothesis for future validation.
- Open Access
- 14 May 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (10) , 4918
Stability-Aware Uplift Policy Selection for Customer Retention: From Predictive Scores to Actionable Segments
Uplift modeling optimizes intervention-based campaigns by identifying customers whose behavior changes exclusively due to specific treatments, moving beyond standard baseline risk predictions. However, in real-world deployments, algorithms that maximize traditional causal ranking metrics (e.g., the Qini coefficient) often fail to be optimal in practice. The inherent variance of Conditional Average Treatment Effect (CATE) estimators exposes critical trade-offs between expected economic value, algorithmic stability, and policy interpretability. To address this gap, this study proposes a stability-aware, value-driven computational framework for selecting an uplift policy. The pipeline evaluates multiple causal and non-causal algorithmic families, including traditional baselines, multimodel approaches, and transformed-outcome variants, within a repeated-run validation protocol. Candidate policies are assessed primarily through incremental revenue and target-set stability, whereas a post hoc surrogate tree distillation step is used to translate the selected policy into interpretable rule-based customer segments. An empirical evaluation of the publicly available Telco Customer Churn dataset under two distinct regimes (a causally controlled semisynthetic scenario and an observational proxy scenario) reveals that the highest-yielding causal policy frequently suffers from severe targeting instability, inducing a clear risk–return trade-off. Furthermore, uplift models outperform traditional baselines in the causally controlled regime, whereas traditional baselines remain economically superior in the confounded proxy settings. Overall, this study establishes that jointly assessing economic utility, algorithmic stability, and transparent segmentation is essential for deploying robust and defensible causal machine learning in production environments.
- 14 May 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (10) , 4918
Open AccessStability-Aware Uplift Policy Selection for Customer Retention: From Predictive Scores to Actionable Segments
Uplift modeling optimizes intervention-based campaigns by identifying customers whose behavior changes exclusively due to specific treatments, moving beyond standard baseline risk predictions. However, in real-world deployments, algorithms that maximize traditional causal ranking metrics (e.g., the Qini coefficient) often fail to be optimal in practice. The inherent variance of Conditional Average Treatment Effect (CATE) estimators exposes critical trade-offs between expected economic value, algorithmic stability, and policy interpretability. To address this gap, this study proposes a stability-aware, value-driven computational framework for selecting an uplift policy. The pipeline evaluates multiple causal and non-causal algorithmic families, including traditional baselines, multimodel approaches, and transformed-outcome variants, within a repeated-run validation protocol. Candidate policies are assessed primarily through incremental revenue and target-set stability, whereas a post hoc surrogate tree distillation step is used to translate the selected policy into interpretable rule-based customer segments. An empirical evaluation of the publicly available Telco Customer Churn dataset under two distinct regimes (a causally controlled semisynthetic scenario and an observational proxy scenario) reveals that the highest-yielding causal policy frequently suffers from severe targeting instability, inducing a clear risk–return trade-off. Furthermore, uplift models outperform traditional baselines in the causally controlled regime, whereas traditional baselines remain economically superior in the confounded proxy settings. Overall, this study establishes that jointly assessing economic utility, algorithmic stability, and transparent segmentation is essential for deploying robust and defensible causal machine learning in production environments.
- Open Access
- 1 January 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (1) , 459
Towards Intelligent Fused Filament Fabrication: Computational Verification of a Monitoring and Early-Warning Framework for Instability Mitigation
Fused Filament Fabrication (FFF) plays a critical role in several application fields due to its affordability and manufacturing versatility. However, FFF reliability remains vulnerable to rapid environmental and operational variations, which directly influence the dimensional precision and mechanical properties of printed parts. To address these challenges, this study presents a simulation-based computational framework for the real-time early-warning supervision of FFF systems. The proposed multilayer architecture integrates high-throughput data acquisition, distributed computing, and dynamic analysis to proactively detect deviations from optimal conditions. Architectural verification follows a simulation-first methodology designed to replicate the operational dynamics of standard FFF hardware. By employing telemetry streams to test the decision-making pipeline, the study isolates computational performance, such as throughput and latency, from the confounding variables of physical hardware. This approach enables a precise, deterministic assessment of the system’s responsiveness, serving as a foundational de-risking step prior to empirical implementation. Numerical results of this study show that the integrated distributed computing model successfully manages high-frequency telemetry with a response time within the operational safety margins, confirming the architectural viability of the proposed solution. By providing insights into system behavior prior to physical deployment, this simulation-first strategy mitigates implementation risks and offers practical guidance for developing autonomous additive manufacturing workflows, advancing the transition toward intelligent industrial FFF.
- 1 January 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (1) , 459
Open AccessTowards Intelligent Fused Filament Fabrication: Computational Verification of a Monitoring and Early-Warning Framework for Instability Mitigation
Fused Filament Fabrication (FFF) plays a critical role in several application fields due to its affordability and manufacturing versatility. However, FFF reliability remains vulnerable to rapid environmental and operational variations, which directly influence the dimensional precision and mechanical properties of printed parts. To address these challenges, this study presents a simulation-based computational framework for the real-time early-warning supervision of FFF systems. The proposed multilayer architecture integrates high-throughput data acquisition, distributed computing, and dynamic analysis to proactively detect deviations from optimal conditions. Architectural verification follows a simulation-first methodology designed to replicate the operational dynamics of standard FFF hardware. By employing telemetry streams to test the decision-making pipeline, the study isolates computational performance, such as throughput and latency, from the confounding variables of physical hardware. This approach enables a precise, deterministic assessment of the system’s responsiveness, serving as a foundational de-risking step prior to empirical implementation. Numerical results of this study show that the integrated distributed computing model successfully manages high-frequency telemetry with a response time within the operational safety margins, confirming the architectural viability of the proposed solution. By providing insights into system behavior prior to physical deployment, this simulation-first strategy mitigates implementation risks and offers practical guidance for developing autonomous additive manufacturing workflows, advancing the transition toward intelligent industrial FFF.
- Open Access
A Knowledge-Driven Framework for AI-Augmented Business Process Management Systems: Bridging Explainability and Agile Knowledge Sharing
Background: The integration of Artificial Intelligence (AI) into Business Process Management Systems (BPMSs) has led to the emergence of AI-Augmented Business Process Management Systems (ABPMSs). These systems offer dynamic adaptation, real-time process optimization, and enhanced knowledge management capabilities. However, key challenges remain, particularly regarding explainability, user engagement, and behavioral integration. Methods: This study presents a novel framework that synergistically integrates the Socialization, Externalization, Combination, and Internalization knowledge model (SECI), Agile methods (specifically Scrum), and cutting-edge AI technologies, including explainable AI (XAI), process mining, and Robotic Process Automation (RPA). The framework enables the formalization, verification, and sharing of knowledge via a well-organized, user-friendly software platform and collaborative practices, especially Communities of Practice (CoPs). Results: The framework emphasizes situation-aware explainability, modular adoption, and continuous improvement to ensure effective human–AI collaboration. It provides theoretical and practical mechanisms for aligning AI capabilities with organizational knowledge management. Conclusions: The proposed framework facilitates the transition from traditional BPMSs to more sophisticated ABPMSs by leveraging structured methodologies and technologies. The approach enhances knowledge exchange and process evolution, supported by detailed modeling using BPMN 2.0.
Open AccessA Knowledge-Driven Framework for AI-Augmented Business Process Management Systems: Bridging Explainability and Agile Knowledge Sharing
Background: The integration of Artificial Intelligence (AI) into Business Process Management Systems (BPMSs) has led to the emergence of AI-Augmented Business Process Management Systems (ABPMSs). These systems offer dynamic adaptation, real-time process optimization, and enhanced knowledge management capabilities. However, key challenges remain, particularly regarding explainability, user engagement, and behavioral integration. Methods: This study presents a novel framework that synergistically integrates the Socialization, Externalization, Combination, and Internalization knowledge model (SECI), Agile methods (specifically Scrum), and cutting-edge AI technologies, including explainable AI (XAI), process mining, and Robotic Process Automation (RPA). The framework enables the formalization, verification, and sharing of knowledge via a well-organized, user-friendly software platform and collaborative practices, especially Communities of Practice (CoPs). Results: The framework emphasizes situation-aware explainability, modular adoption, and continuous improvement to ensure effective human–AI collaboration. It provides theoretical and practical mechanisms for aligning AI capabilities with organizational knowledge management. Conclusions: The proposed framework facilitates the transition from traditional BPMSs to more sophisticated ABPMSs by leveraging structured methodologies and technologies. The approach enhances knowledge exchange and process evolution, supported by detailed modeling using BPMN 2.0.
- Open Access
- 4 January 2025
- Published by MDPI AG in Algorithms
- Vol. 18 (1) , 22
A Scalable Framework for Sensor Data Ingestion and Real-Time Processing in Cloud Manufacturing
Cloud Manufacturing enables the integration of geographically distributed manufacturing resources through advanced Cloud Computing and IoT technologies. This paradigm promotes the development of scalable and adaptable production systems. However, existing frameworks face challenges related to scalability, resource orchestration, and data security, particularly in rapidly evolving decentralized manufacturing settings. This study presents a novel nine-layer architecture designed specifically to address these issues. Central to this framework is the use of Apache Kafka for robust, high-throughput data ingestion, and Apache Spark Streaming to enhance real-time data processing. This framework is underpinned by a microservice-based architecture that ensures a high scalability and reduced latency. Experimental validation using sensor data from the UCI Machine Learning Repository demonstrated substantial improvements in processing efficiency and throughput compared with conventional frameworks. Key components, such as RabbitMQ, contribute to low-latency performance, whereas Kafka ensures data durability and supports real-time application. Additionally, the in-memory data processing of Spark Streaming enables rapid and dynamic data analysis, yielding actionable insights. The experimental results highlight the potential of the framework to enhance operational efficiency, resource utilization, and data security, offering a resilient solution suited to the demands of modern industrial applications. This study underscores the contribution of the framework to advancing Cloud Manufacturing by providing detailed insights into its performance, scalability, and applicability to contemporary manufacturing ecosystems.
- 4 January 2025
- Published by MDPI AG in Algorithms
- Vol. 18 (1) , 22
Open AccessA Scalable Framework for Sensor Data Ingestion and Real-Time Processing in Cloud Manufacturing
Cloud Manufacturing enables the integration of geographically distributed manufacturing resources through advanced Cloud Computing and IoT technologies. This paradigm promotes the development of scalable and adaptable production systems. However, existing frameworks face challenges related to scalability, resource orchestration, and data security, particularly in rapidly evolving decentralized manufacturing settings. This study presents a novel nine-layer architecture designed specifically to address these issues. Central to this framework is the use of Apache Kafka for robust, high-throughput data ingestion, and Apache Spark Streaming to enhance real-time data processing. This framework is underpinned by a microservice-based architecture that ensures a high scalability and reduced latency. Experimental validation using sensor data from the UCI Machine Learning Repository demonstrated substantial improvements in processing efficiency and throughput compared with conventional frameworks. Key components, such as RabbitMQ, contribute to low-latency performance, whereas Kafka ensures data durability and supports real-time application. Additionally, the in-memory data processing of Spark Streaming enables rapid and dynamic data analysis, yielding actionable insights. The experimental results highlight the potential of the framework to enhance operational efficiency, resource utilization, and data security, offering a resilient solution suited to the demands of modern industrial applications. This study underscores the contribution of the framework to advancing Cloud Manufacturing by providing detailed insights into its performance, scalability, and applicability to contemporary manufacturing ecosystems.
- Open Access
- 11 April 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (8) , 3217
On Integrating Time-Series Modeling with Long Short-Term Memory and Bayesian Optimization: A Comparative Analysis for Photovoltaic Power Forecasting
The means of energy generation are rapidly progressing as production shifts from a centralized model to a fully decentralized one that relies on renewable energy sources. Energy generation is intermittent and difficult to control owing to the high variability in the weather parameters. Consequently, accurate forecasting has gained increased significance in ensuring a balance between energy supply and demand with maximum efficiency and sustainability. Despite numerous studies on this issue, large sample datasets and measurements of meteorological variables at plant sites are generally required to obtain a higher prediction accuracy. In practical applications, we often encounter the problem of insufficient sample data, which makes it challenging to accurately forecast energy production with limited data. The Holt–Winters exponential smoothing method is a statistical tool that is frequently employed to forecast periodic series, owing to its low demand for training data and high forecasting accuracy. However, this model has limitations, particularly when handling time-series analysis for long-horizon predictions. To overcome this shortcoming, this study proposes an integrated approach that combines the Holt–Winters exponential smoothing method with long short-term memory and Bayesian optimization to handle long-range dependencies. For illustrative purposes, this new method is applied to forecast rooftop photovoltaic production in a real-world case study, where it is assumed that measurements of meteorological variables (such as solar irradiance and temperature) at the plant site are not available. Through our analysis, we found that by utilizing these methods in combination, we can develop more accurate and reliable forecasting models that can inform decision-making and resource management in this field.
- 11 April 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (8) , 3217
Open AccessOn Integrating Time-Series Modeling with Long Short-Term Memory and Bayesian Optimization: A Comparative Analysis for Photovoltaic Power Forecasting
The means of energy generation are rapidly progressing as production shifts from a centralized model to a fully decentralized one that relies on renewable energy sources. Energy generation is intermittent and difficult to control owing to the high variability in the weather parameters. Consequently, accurate forecasting has gained increased significance in ensuring a balance between energy supply and demand with maximum efficiency and sustainability. Despite numerous studies on this issue, large sample datasets and measurements of meteorological variables at plant sites are generally required to obtain a higher prediction accuracy. In practical applications, we often encounter the problem of insufficient sample data, which makes it challenging to accurately forecast energy production with limited data. The Holt–Winters exponential smoothing method is a statistical tool that is frequently employed to forecast periodic series, owing to its low demand for training data and high forecasting accuracy. However, this model has limitations, particularly when handling time-series analysis for long-horizon predictions. To overcome this shortcoming, this study proposes an integrated approach that combines the Holt–Winters exponential smoothing method with long short-term memory and Bayesian optimization to handle long-range dependencies. For illustrative purposes, this new method is applied to forecast rooftop photovoltaic production in a real-world case study, where it is assumed that measurements of meteorological variables (such as solar irradiance and temperature) at the plant site are not available. Through our analysis, we found that by utilizing these methods in combination, we can develop more accurate and reliable forecasting models that can inform decision-making and resource management in this field.
- Open Access
- 14 January 2024
- Published by MDPI AG in Sustainability
- Vol. 16 (2) , 714
An Assessment of Digitalization Techniques in Contact Centers and Their Impact on Agent Performance and Well-Being
The role of contact centers in improving the operational efficiency of numerous organizations is of utmost importance. Presently, digitalization technology has enabled contact centers to deliver exceptional customer service and support, while minimizing the adverse impact on agent well-being. Artificial intelligence techniques such as topic modeling and sentiment analysis can aid agents in addressing specific queries, providing real-time support and feedback, and helping them build stronger relationships with customers. This study aims to investigate the advantages of integrating these techniques in the analysis of customer–agent conversations within contact centers. This study examines whether there is a discernible advantage in analyzing customer–agent conversations in real-time and whether it is worth using this type of digitization to enhance agent performance and well-being. Furthermore, this study explores the impact of these technologies on European privacy, business, real-time agent support, the value of conversation data, brand reputation, and customer satisfaction. The results of this study demonstrate the significance of incorporating topic modeling and sentiment analysis into the analysis of customer–agent conversations at contact centers.
- 14 January 2024
- Published by MDPI AG in Sustainability
- Vol. 16 (2) , 714
Open AccessAn Assessment of Digitalization Techniques in Contact Centers and Their Impact on Agent Performance and Well-Being
The role of contact centers in improving the operational efficiency of numerous organizations is of utmost importance. Presently, digitalization technology has enabled contact centers to deliver exceptional customer service and support, while minimizing the adverse impact on agent well-being. Artificial intelligence techniques such as topic modeling and sentiment analysis can aid agents in addressing specific queries, providing real-time support and feedback, and helping them build stronger relationships with customers. This study aims to investigate the advantages of integrating these techniques in the analysis of customer–agent conversations within contact centers. This study examines whether there is a discernible advantage in analyzing customer–agent conversations in real-time and whether it is worth using this type of digitization to enhance agent performance and well-being. Furthermore, this study explores the impact of these technologies on European privacy, business, real-time agent support, the value of conversation data, brand reputation, and customer satisfaction. The results of this study demonstrate the significance of incorporating topic modeling and sentiment analysis into the analysis of customer–agent conversations at contact centers.
- Open Access
- 15 November 2023
- Published by MDPI AG in Algorithms
- Vol. 16 (11) , 524
Utilizing Mixture Regression Models for Clustering Time-Series Energy Consumption of a Plastic Injection Molding Process
Considering the issue of energy consumption reduction in industrial plants, we investigated a clustering method for mining the time-series data related to energy consumption. The industrial case study considered in our work is one of the most energy-intensive processes in the plastics industry: the plastic injection molding process. Concerning the industrial setting, the energy consumption of the injection molding machine was monitored across multiple injection molding cycles. The collected data were then analyzed to establish patterns and trends in the energy consumption of the injection molding process. To this end, we considered mixtures of regression models given their flexibility in modeling heterogeneous time series and clustering time series in an unsupervised machine learning framework. Given the assumption of autocorrelated data and exogenous variables in the mixture model, we implemented an algorithm for model fitting that combined autocorrelated observations with spline and polynomial regressions. Our results demonstrate an accurate grouping of energy-consumption profiles, where each cluster is related to a specific production schedule. The clustering method also provides a unique profile of energy consumption for each cluster, depending on the production schedule and regression approach (i.e., spline and polynomial). According to these profiles, information related to the shape of energy consumption was identified, providing insights into reducing the electrical demand of the plant.
- 15 November 2023
- Published by MDPI AG in Algorithms
- Vol. 16 (11) , 524
Open AccessUtilizing Mixture Regression Models for Clustering Time-Series Energy Consumption of a Plastic Injection Molding Process
Considering the issue of energy consumption reduction in industrial plants, we investigated a clustering method for mining the time-series data related to energy consumption. The industrial case study considered in our work is one of the most energy-intensive processes in the plastics industry: the plastic injection molding process. Concerning the industrial setting, the energy consumption of the injection molding machine was monitored across multiple injection molding cycles. The collected data were then analyzed to establish patterns and trends in the energy consumption of the injection molding process. To this end, we considered mixtures of regression models given their flexibility in modeling heterogeneous time series and clustering time series in an unsupervised machine learning framework. Given the assumption of autocorrelated data and exogenous variables in the mixture model, we implemented an algorithm for model fitting that combined autocorrelated observations with spline and polynomial regressions. Our results demonstrate an accurate grouping of energy-consumption profiles, where each cluster is related to a specific production schedule. The clustering method also provides a unique profile of energy consumption for each cluster, depending on the production schedule and regression approach (i.e., spline and polynomial). According to these profiles, information related to the shape of energy consumption was identified, providing insights into reducing the electrical demand of the plant.
- Open Access
- 8 February 2023
- Published by MDPI AG in Algorithms
- Vol. 16 (2) , 94
A Comparison of Different Topic Modeling Methods through a Real Case Study of Italian Customer Care
The paper deals with the analysis of conversation transcriptions between customers and agents in a call center of a customer care service. The objective is to support the analysis of text transcription of human-to-human conversations, to obtain reports on customer problems and complaints, and on the way an agent has solved them. The aim is to provide customer care service with a high level of efficiency and user satisfaction. To this aim, topic modeling is considered since it facilitates insightful analysis from large documents and datasets, such as a summarization of the main topics and topic characteristics. This paper presents a performance comparison of four topic modeling algorithms: (i) Latent Dirichlet Allocation (LDA); (ii) Non-negative Matrix Factorization (NMF); (iii) Neural-ProdLDA (Neural LDA) and Contextualized Topic Models (CTM). The comparison study is based on a database containing real conversation transcriptions in Italian Natural Language. Experimental results and different topic evaluation metrics are analyzed in this paper to determine the most suitable model for the case study. The gained knowledge can be exploited by practitioners to identify the optimal strategy and to perform and evaluate topic modeling on Italian natural language transcriptions of human-to-human conversations. This work can be an asset for grounding applications of topic modeling and can be inspiring for similar case studies in the domain of customer care quality.
- 8 February 2023
- Published by MDPI AG in Algorithms
- Vol. 16 (2) , 94
Open AccessA Comparison of Different Topic Modeling Methods through a Real Case Study of Italian Customer Care
The paper deals with the analysis of conversation transcriptions between customers and agents in a call center of a customer care service. The objective is to support the analysis of text transcription of human-to-human conversations, to obtain reports on customer problems and complaints, and on the way an agent has solved them. The aim is to provide customer care service with a high level of efficiency and user satisfaction. To this aim, topic modeling is considered since it facilitates insightful analysis from large documents and datasets, such as a summarization of the main topics and topic characteristics. This paper presents a performance comparison of four topic modeling algorithms: (i) Latent Dirichlet Allocation (LDA); (ii) Non-negative Matrix Factorization (NMF); (iii) Neural-ProdLDA (Neural LDA) and Contextualized Topic Models (CTM). The comparison study is based on a database containing real conversation transcriptions in Italian Natural Language. Experimental results and different topic evaluation metrics are analyzed in this paper to determine the most suitable model for the case study. The gained knowledge can be exploited by practitioners to identify the optimal strategy and to perform and evaluate topic modeling on Italian natural language transcriptions of human-to-human conversations. This work can be an asset for grounding applications of topic modeling and can be inspiring for similar case studies in the domain of customer care quality.
- Open Access
- 13 June 2022
- Published by MDPI AG in Algorithms
- Vol. 15 (6) , 204
Topic Modeling for Automatic Analysis of Natural Language: A Case Study in an Italian Customer Support Center
This paper focuses on the automatic analysis of conversation transcriptions in the call center of a customer care service. The goal is to recognize topics related to problems and complaints discussed in several dialogues between customers and agents. Our study aims to implement a framework able to automatically cluster conversation transcriptions into cohesive and well-separated groups based on the content of the data. The framework can alleviate the analyst selecting proper values for the analysis and the clustering processes. To pursue this goal, we consider a probabilistic model based on the latent Dirichlet allocation, which associates transcriptions with a mixture of topics in different proportions. A case study consisting of transcriptions in the Italian natural language, and collected in a customer support center of an energy supplier, is considered in the paper. Performance comparison of different inference techniques is discussed using the case study. The experimental results demonstrate the approach’s efficacy in clustering Italian conversation transcriptions. It also results in a practical tool to simplify the analytic process and off-load the parameter tuning from the end-user. According to recent works in the literature, this paper may be valuable for introducing latent Dirichlet allocation approaches in topic modeling for the Italian natural language.
- 13 June 2022
- Published by MDPI AG in Algorithms
- Vol. 15 (6) , 204
Open AccessTopic Modeling for Automatic Analysis of Natural Language: A Case Study in an Italian Customer Support Center
This paper focuses on the automatic analysis of conversation transcriptions in the call center of a customer care service. The goal is to recognize topics related to problems and complaints discussed in several dialogues between customers and agents. Our study aims to implement a framework able to automatically cluster conversation transcriptions into cohesive and well-separated groups based on the content of the data. The framework can alleviate the analyst selecting proper values for the analysis and the clustering processes. To pursue this goal, we consider a probabilistic model based on the latent Dirichlet allocation, which associates transcriptions with a mixture of topics in different proportions. A case study consisting of transcriptions in the Italian natural language, and collected in a customer support center of an energy supplier, is considered in the paper. Performance comparison of different inference techniques is discussed using the case study. The experimental results demonstrate the approach’s efficacy in clustering Italian conversation transcriptions. It also results in a practical tool to simplify the analytic process and off-load the parameter tuning from the end-user. According to recent works in the literature, this paper may be valuable for introducing latent Dirichlet allocation approaches in topic modeling for the Italian natural language.