Multi-lingual opinion mining for social media discourses: an approach using deep learning based hybrid fine-tuned smith algorithm with adam optimizer

Shahade, Aniket K; Walse, K. H.; Thakare, V. M.; Atique, Mohammad

doi:10.1016/j.jjimei.2023.100182

Cited by 8 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, in the context of system robustness, it’s important to consider the impact of class imbalance and explore alternative metrics to ensure a comprehensive evaluation. To address this issue, we used precision, system robustness, and variance to cover problem when the F1 score is affected by the imbalance in class distribution (Gkikas et al ., 2022; Shahade et al ., 2023).…”

Section: Case Studies and Finding The Resultsmentioning

confidence: 99%

Unveiling just-in-time decision support system using social media analytics: a case study on reverse logistics resource recycling

Shahidzadeh,

Shokouhyar

2024

IMDS

View full text Add to dashboard Cite

PurposeIn recent times, the field of corporate intelligence has gained substantial prominence, employing advanced data analysis techniques to yield pivotal insights for instantaneous strategic and tactical decision-making. Expanding beyond rudimentary post observation and analysis, social media analytics unfolds a comprehensive exploration of diverse data streams encompassing social media platforms and blogs, thereby facilitating an all-encompassing understanding of the dynamic social customer landscape. During an extensive evaluation of social media presence, various indicators such as popularity, impressions, user engagement, content flow, and brand references undergo meticulous scrutiny. Invaluable intelligence lies within user-generated data stemming from social media platforms, encompassing valuable customer perspectives, feedback, and recommendations that have the potential to revolutionize numerous operational facets, including supply chain management. Despite its intrinsic worth, the actual business value of social media data is frequently overshadowed due to the pervasive abundance of content saturating the digital realm. In response to this concern, the present study introduces a cutting-edge system known as the Enterprise Just-in-time Decision Support System (EJDSS).Design/methodology/approachLeveraging deep learning techniques and advanced analytics of social media data, the EJDSS aims to propel business operations forward. Specifically tailored to the domain of marketing, the framework delineates a practical methodology for extracting invaluable insights from the vast expanse of social data. This scholarly work offers a comprehensive overview of fundamental principles, pertinent challenges, functional aspects, and significant advancements in the realm of extensive social data analysis. Moreover, it presents compelling real-world scenarios that vividly illustrate the tangible advantages companies stand to gain by incorporating social data analytics into their decision-making processes and capitalizing on emerging investment prospects.FindingsTo substantiate the efficacy of the EJDSS, a detailed case study centered around reverse logistics resource recycling is presented, accompanied by experimental findings that underscore the system’s exceptional performance. The study showcases remarkable precision, robustness, F1 score, and variance statistics, attaining impressive figures of 83.62%, 78.44%, 83.67%, and 3.79%, respectively.Originality/valueThis scholarly work offers a comprehensive overview of fundamental principles, pertinent challenges, functional aspects, and significant advancements in the realm of extensive social data analysis. Moreover, it presents compelling real-world scenarios that vividly illustrate the tangible advantages companies stand to gain by incorporating social data analytics into their decision-making processes and capitalizing on emerging investment prospects.

show abstract

Section: Case Studies and Finding The Resultsmentioning

confidence: 99%

Unveiling just-in-time decision support system using social media analytics: a case study on reverse logistics resource recycling

Shahidzadeh,

Shokouhyar

2024

IMDS

View full text Add to dashboard Cite

show abstract

“…Using a single-layer LSTM model, we assessed the performance of the PM 2.5 concentration prediction. The chosen optimizer and loss function were "Adam" [40] and "MAE", respectively. Throughout the experiments, the inclusion of additional related features led to an expansion of the design input factors, as outlined in detail in Table 1.…”

Section: Methods and Technical Roadmap 231 The Structure Of The Exper...mentioning

confidence: 99%

An Evaluation of the Influence of Meteorological Factors and a Pollutant Emission Inventory on PM2.5 Prediction in the Beijing–Tianjin–Hebei Region Based on a Deep Learning Method

Shi,

Li,

Gao

et al. 2024

Environments

View full text Add to dashboard Cite

In this study, a Long Short-Term Memory (LSTM) network approach is employed to evaluate the prediction performance of PM2.5 in the Beijing–Tianjin–Hebei region (BTH). The proposed method is evaluated using the hourly air quality datasets from the China National Environmental Monitoring Center, European Center for Medium-range Weather Forecasts ERA5 (ECMWF-ERA5), and Multi-resolution Emission Inventory for China (MEIC) for the years 2016 and 2017. The predicted PM2.5 concentrations demonstrate a strong correlation with the observed values (R2 = 0.871–0.940) in the air quality dataset. Furthermore, the model exhibited the best performance in situations of heavy pollution (PM2.5 > 150 μg/m3) and during the winter season, with respective R2 values of 0.689 and 0.915. In addition, the influence of ECMWF-ERA5’s hourly meteorological factors was assessed, and the results revealed regional heterogeneity on a large scale. Further evaluation was conducted by analyzing the chemical components of the MEIC inventory on the prediction performance. We concluded that the same temporal profile may not be suitable for addressing emission inventories in a large area with a deep learning method.

show abstract

Hybrid modeling techniques for predicting chemical oxygen demand in wastewater treatment: a stacking ensemble learning approach with neural networks

Tuppad

2024

Environ Monit Assess

View full text Add to dashboard Cite

Multi-lingual opinion mining for social media discourses: an approach using deep learning based hybrid fine-tuned smith algorithm with adam optimizer

Cited by 8 publications

References 27 publications

Unveiling just-in-time decision support system using social media analytics: a case study on reverse logistics resource recycling

Unveiling just-in-time decision support system using social media analytics: a case study on reverse logistics resource recycling

An Evaluation of the Influence of Meteorological Factors and a Pollutant Emission Inventory on PM2.5 Prediction in the Beijing–Tianjin–Hebei Region Based on a Deep Learning Method

Hybrid modeling techniques for predicting chemical oxygen demand in wastewater treatment: a stacking ensemble learning approach with neural networks

Contact Info

Product

Resources

About