Conversion Process Research Articles

Study on the Applicability of Autothermic Pyrolysis In Situ Conversion Process for Low-Grade Oil Shale: A Case Study of Tongchuan, Ordos Basin, China

The feasibility of the autothermic pyrolysis in situ conversion (ATS) process for low-grade oil shale (OS) has not been determined. In this research, the pyrolysis and combustion properties of Tongchuan OS, with a 4.04% oil yield, were systematically analyzed. The findings revealed that temperatures between 350 and 425 °C favored oil production, while temperatures from 450 to 520 °C resulted in a higher rate of gaseous generation. At 300 °C, the volume expansion and ignition coking caused by the large amount of bitumen generated resulted in severe pore plugging, which significantly increased the combustion activation energy of the residue, while the presence of substantial flammable bitumen also significantly decreased the ignition and combustion temperatures. From 300 to 520 °C, the combustion performance of residue decreases continuously. In addition, pyrolysis residues of Tongchuan exhibited a slightly higher calorific value, between 425 and 520 °C, owing to its higher fixed carbon content (10.79%). Based on the ideal temperature screening method outlined for Tongchuan OS, the recommended preheating temperature for Tongchuan OS was 425 °C, while the optimum temperature for the retorting zone should be 510 °C, considering a heat utilization rate of 40%. These findings contribute valuable insights for the application of the ATS process to low-grade OS.

A machine learning and CFD modeling hybrid approach for predicting real-time heat transfer during cokemaking processes

As the development of green energy and smart industries progresses, concerted efforts are being directed towards the transformation of coking industries. Effective management of heat transfer during the coking process is essential to fortify energy consumption management and augment the quality of coke produced. However, the process during cokemaking is a complex thermochemical conversion process where even minor deviations in operating conditions can lead to instability. Additionally, due to the environmental and chemical conditions inside the coke oven, temperature measurements during operation are difficult. As the fields of Industry 4.0 continue to evolve, numerous industries have begun to leverage intelligent strategies to enhance advanced process management. The digital twin (DG) technique stands as a pivotal technology in the realm of industrial transformation, paving the way for a smarter future. However, given the inherent difficulty in real-time data collection for process operations, the challenge of achieving synchronization becomes increasingly prevalent in the development of DG for the smart coking process. As a result, predicting changes in coal temperature during the cokemaking process is crucial. Currently, computer technology allows for the simulation of complex chemical processes. While some numerical models describe the cokemaking process, these models are limited by the time-consuming characteristic and computing resources. To address this issue, this study proposed a Machine Learning (ML) and Computational Fluid Dynamics (CFD) hybrid model for real-time prediction of heat transfer during the cokemaking process. A CFD model was built based on an industrial-scale coke oven, with cokemaking process data generated through CFD simulation serving as input for the ML models. This study used a total of nine ML models, including ensemble and deep learning models. The hyperparameters of each model were optimized by Grey Wolf Optimization (GWO), Particle Swarm Optimization (PSO), and JAYA algorithms to identify the optimal model structure. Both simulation and empirical experimentation using a coke oven, coupled with industrial data verification, have substantiated the superiority of the proposed model. It simulates the heat transfer during the coking process with high accuracy and efficiency, thereby demonstrating its capacity to significantly reduce energy consumption within the coking industry.

A comprehensive assessment of photosynthetic acclimation to shade in C4 grass (Cynodon dactylon (L.) Pers.)

BackgroundLight deficit in shaded environment critically impacts the growth and development of turf plants. Despite this fact, past research has predominantly concentrated on shade avoidance rather than shade tolerance. To address this, our study examined the photosynthetic adjustments of Bermudagrass when exposed to varying intensities of shade to gain an integrative understanding of the shade response of C4 turfgrass.ResultsWe observed alterations in photosynthetic pigment-proteins, electron transport and its associated carbon and nitrogen assimilation, along with ROS-scavenging enzyme activity in shaded conditions. Mild shade enriched Chl b and LHC transcripts, while severe shade promoted Chl a, carotenoids and photosynthetic electron transfer beyond QA− (ET0/RC, φE0, Ψ0). The study also highlighted differential effects of shade on leaf and root components. For example, Soluble sugar content varied between leaves and roots as shade diminished SPS, SUT1 but upregulated BAM. Furthermore, we observed that shading decreased the transcriptional level of genes involving in nitrogen assimilation (e.g. NR) and SOD, POD, CAT enzyme activities in leaves, even though it increased in roots.ConclusionsAs shade intensity increased, considerable changes were noted in light energy conversion and photosynthetic metabolism processes along the electron transport chain axis. Our study thus provides valuable theoretical groundwork for understanding how C4 grass acclimates to shade tolerance.

Coordinated configuration of hybrid energy storage for electricity-hydrogen integrated energy system

This paper proposes an optimal coordinated configuration method of hybrid electricity and hydrogen storage for the electricity‑hydrogen integrated energy system (EH-ES) to promote the renewable energy source (RES) utilization and reduce the deployment cost. To simulate the practical operation of EH-ES, an energy hub framework with a discrete state space system matrix is designed to characterize the internal interconnection topology and quantify the steady-state production, storage, conversion and utilization processes of electricity and hydrogen energy carriers within EH-ES. A chronological operation simulation based electricity and hydrogen storage configuration model over a year-round time horizon is formulated to collaboratively optimize the capacity of the electrolyzer, fuel cell, battery energy storage (BES) and hydrogen storage tank. In this model, the power and capacity complementarity of BES and generalized hydrogen storage is fully exploited to compensate for power and energy imbalances, and additional capacity configuration of BES is considered to mitigate the drastic electrolytic power fluctuation. Besides, a typical source-load scenario reduction method based on K-means and ordered clustering is developed to avoid a large number of operation variables due to year-round hourly simulation. Comparative studies demonstrate that the proposed methodology can achieve the RES consumption rate of 98.873 % while the equipment investment cost can be reduced by 10.034 %.

Energy Barriers and Gap Between Two Excited States in a Dual-Emissive Carborane.

A thorough understanding of the internal conversion process between excited states is important for the designing of ideal multiple-emissive materials. However, it is hard to experimentally measure both the energy barriers and gaps between the excited states of a compound. For a long time, it is dubious if what was measured is the energy gap or barrier between two excited states. In this paper, we designed 1-(pyren-2'-yl)-9,12-di(p-tolyl)-o-carborane (2), which shows dual-emission in solution. Temperature-dependent fluorescence measurements show that the two emission bands in hexane are corresponding to two different excited states. The ratio of the emission bands is controlled by thermodynamics at higher temperatures and by kinetics at lower temperatures. Thus, the energy barrier and energy gaps between the two excited states of 2 can be experimentally estimated.

Coordination Microenvironment Regulation in Carbon−Based Atomically Dispersed Metal Catalysts for Clean Energy−Conversion

AbstractEmerging atomically dispersed metal catalysts (ADCs), especially carbon−based ADCs have arguably received enormous attention in diverse electrochemical energy conversion processes. Such catalysts have well−defined active centers, and their geometric and electronic structures depend greatly on their coordination microenvironments, which, in turn, govern the performances in the realm of electrocatalysis. In this review, it is focused on the state−of−the−art synthesis strategies for carbon−based ADCs, with particular emphasis on their microenvironment modulations. The advances in characterizing the microenvironment alongside understanding the synthetic pathway are outlined, and exemplified in electrochemical applications, including electrocatalytic H2 evolution, O2 evolution/reduction, CO2 reduction, and Li polysulfides conversion reactions. Rather than focusing on the catalysis metrics, this review delved deeply into the underly science and the associated reaction mechanisms of these catalysts in diverse electrochemical systems. The fundamental impacts of the microenvironments of the catalysts on electrocatalytic activities, selectivities, and stabilities are discussed. In the end, it is concluded by highlighting the current issues of the microenvironment engineering of these carbon−based ADCs and propose the prospects for future opportunities and challenges.

Nonthermal plasma removal of CH4-NOx under LNG engine exhaust environment: experiment, mechanism and kinetic analysis

To explore the mechanism underlying the removal of CH4 and NOx, which are typical emissions from LNG engines, through the nonthermal plasma method, a plasma chemistry model of CH4-NOx under the LNG engine exhaust environment was established in this study. Sixty key reactions affecting the conversion of CH4, CO, and NOx were determined through sensitivity analysis, and their pre-exponential factors were optimized using a genetic algorithm. The proposed model shows good performance in predicting the concentrations of CH4, CO, and NOx under the exhaust conditions of LNG engine. Then, reaction path analyses for evolution of CH4, CO, NO, and NO2 were performed under specific conditions. The results showed that CH4 mainly decomposed into CH2 that is subsequently converted into CO and CO2. CH2 is the main source for CO production. The concentration of NOx is determined by the oxidation reactions of N with O2, OH, and HO2. The specific concentration distributions of NO and NO2 were influenced by the oxidation–reduction reactions between them. Analyses of the time scales for the conversion processes of CH4, CO, and NOx were also conducted, and it was found that the reaction time scales of CH4 and CO were approximately 1 × 10−10−1 × 10−5 s, and that was approximately 1 × 10−9−1 × 10−4 s for NOx. Furthermore, during the overlapping period for the conversion of CH4, CO, and NOx, the NOx was dominant in the competition for O. This study provides a basis for the construction of a plasma catalytic chemistry model of CH4-NOx under LNG engine exhaust conditions.

Simultaneously Regulating Electrochemical Corrosion Behavior and Wettability of Magnesium-Neodymium Alloy by Self-Layered Chemical Conversion Coating.

Rapid corrosion in aqueous solutions of magnesium alloys is one of the major obstacles to their wide application, and coating plays a crucial role in their corrosion protection. Recently, protection- and function-integrated coatings have attracted much attention in the research field of magnesium alloys. In this work, a simple chemical conversion process is proposed to fabricate a composite coating on a magnesium-neodymium alloy through immersion in an aqueous solution made of Ca(OH)2 and NaHCO3. After the immersion process, a coating consisting of two spontaneously formed layers is acquired. The top flower-like layer is composed of Mg5(OH)2(CO3)4∙4H2O, Mg(OH)2 and CaCO3, and the inner dense layer is speculated to be Mg(OH)2. Electrochemical impedance spectroscopy, polarization tests, and hydrogen evolution are combined to evaluate the corrosion resistance in simulated body fluid, simulated seawater solution, and simulated concrete pore solution, which reveals that the coated sample has better corrosion resistance than the uncoated one. After the coated sample is modified with fluorinated silane, a water-repellent surface can be achieved with an average water contact angle of 151.74° and a sliding angle of about 4°. Therefore, our results indicate that effective corrosion protection and potential self-cleaning ability have been integrated on the surface of the magnesium alloy in this study. In addition, the formation mechanism of the self-layered coating is discussed from the viewpoint of the interaction between the substrate and its external solution.

Multi-stimuli-responsive luminescent switching properties of cycloplatinated(II) complexes bearing 2-phenylpyridine derivatives

Three new cycloplatinated(II) complexes, Pt(ppy)L (1), Pt[(CF3)ppy]L (2) and Pt[dF(CF3)ppy]L (3) based on 2-phenylpyridine (ppy), 2-phenyl-5-(trifluoromethyl)pyridine [(CF3)ppy], 2-(2,4-Difluorophenyl)-5-(trifluoromethyl)pyridine [dF(CF3)ppy] and 4-[2-(4-fluorophenyl)ethynyl]-2-pyridinecarboxylic acid (L) ligands were synthesized and characterized. Complex 1 has one metastable structure and exhibits reversible mechanoluminescent property. On the contrary, complexes 2 and 3 each have five types of metastable structures and exhibit multi-stimuli-responsive luminescent switching properties triggered by VOC vapors absorption, heating, and mechanical grinding. Moreover, complexes 2 and 3 display a series of untraditional luminescent switching behaviors such as two-step conversion processes, irreversible process and more than one thermally stable products. Systematic studies on crystal structure, luminescence spectra, PXRD and DFT theoretical calculation demonstrate that the luminescent switching properties of these complexes are attributed to the formation/elimination of intermolecular Pt-Pt interactions during structural conversion processes between metastable structures, which lead to the transformation of the lowest energy excited states between MLCT and MMLCT transitions. Furthermore, the unconventional luminescent switching behaviors are due to the high stability of the metastable structures. In addition, the studies also reveal that the stacking structure of complex can affect its luminescent switching behavior, while the good molecular planarity of the complex is not conducive to the luminescent switching properties.

Terahertz photon to dc current conversion via magnetic excitations of multiferroics

Direct conversion from terahertz photon to charge current is a key phenomenon for terahertz photonics. Quantum geometrical description of optical processes in crystalline solids predicts existence of field-unbiased dc photocurrent arising from terahertz-light generation of magnetic excitations in multiferroics, potentially leading to fast and energy-efficient terahertz devices. Here, we demonstrate the dc charge current generation from terahertz magnetic excitations in multiferroic perovskite manganites with spin-driven ferroelectricity, while keeping an insulating state with no free carrier. It is also revealed that electromagnon, which ranges sub-terahertz to 2 THz, as well as antiferromagnetic resonance shows the giant conversion efficiency. Polar asymmetry induced by the cycloidal spin order gives rise to this terahertz-photon-induced dc photocurrent, and no external magnetic and electric bias field are required for this conversion process. The observed phenomena are beyond the conventional photovoltaics in semi-classical regime and demonstrate the essential role of quantum geometrical aspect in low-energy optical processes. Our finding establishes a paradigm of terahertz photovoltaic phenomena, paving a way for terahertz photonic devices and energy harvesting.

An Efficient Approach to Extract and Store Big Semantic Web Data Using Hadoop and Apache Spark GraphX

The volume of data is growing at an astonishingly high speed. Traditional techniques for storing and processing data, such as relational and centralized databases, have become inefficient and time-consuming. Linked data and the Semantic Web make internet data machine-readable. Because of the increasing volume of linked data and Semantic Web data, storing and working with them using traditional approaches is not enough, and this causes limited hardware resources. To solve this problem, storing datasets using distributed and clustered methods is essential. Hadoop can store datasets because it can use many hard disks for distributed data clustering; Apache Spark can be used for parallel data processing more efficiently than Hadoop MapReduce because Spark uses memory instead of the hard disk. Semantic Web data has been stored and processed in this paper using Apache Spark GraphX and the Hadoop Distributed File System (HDFS). Spark's in-memory processing and distributed computing enable efficient data analysis of massive datasets stored in HDFS. Spark GraphX allows graph-based semantic web data processing. The fundamental objective of this work is to provide a way for efficiently combining Semantic Web and big data technologies to utilize their combined strengths in data analysis and processing. First, the proposed approach uses the SPARQL query language to extract Semantic Web data from DBpedia datasets. DBpedia is a hugely available Semantic Web dataset built on Wikipedia. Secondly, the extracted Semantic Web data was converted to the GraphX data format; vertices and edges files were generated. The conversion process is implemented using Apache Spark GraphX. Third, both vertices and edge tables are stored in HDFS and are available for visualization and analysis operations. Furthermore, the proposed techniques improve the data storage efficiency by reducing the amount of storage space by half when converting from Semantic Web Data to a GraphX file, meaning the RDF size is around 133.8 and GraphX is 75.3. Adopting parallel data processing provided by Apache Spark in the proposed technique reduces the required data processing and analysis time. This article concludes that Apache Spark GraphX can enhance Semantic Web and Big Data technologies. We minimize data size and processing time by converting Semantic Web data to GraphX format, enabling efficient data management and seamless integration.

Mirror Plane Effect of Magnetoplumbite-Type Oxide Restraining Long-Chain Polysulfides Disproportionation for High Loading Lithium Sulfur Batteries.

A facile solid-state approach is employed to synthesize a novel magnetoplumbite-type oxide of NdMgAl11O19, which integrates spinel-stacking layers (MgAl2O4) with Nd-O6 mirror plane structures. The resulting NdMgAl11O19 exhibits remarkable catalytic activity and conversion efficiency during the sulfur reduction reaction (SRR) in lithium-sulfur batteries. By employing the 2D projection mapping technique of in situ confocal Raman spectroscopy and electrochemical technique, it is discovered that the exposed mirror plane structure of Nd-O6 can effectively suppress the undesiring disproportionation reaction (S8 2-→S6 2-+1/4 S8) of long-chain lithium polysulfides at the initial stages of sulfur reduction, thereby promoting the positive process of sulfur to lithium sulfide. This not only mitigates the issue of sulfur shuttle loss but also significantly improve the kinetics of the conversion process. Leveraging these advantages, the NdMgAl11O19/S cathode delivered an impressive initial capacity of up to 1398 mAh g-1 at an electrolyte/sulfur (E/S) ratio of 5.1µL mg-1 and a sulfur loading of 2.3mg cm-2. Even when the sulfur loading is increased to 10.02mg cm-2, the cathode retained a reversible areal capacity of 10.01 mAh cm-2 after 200 cycles. This mirror engineering strategy provides valuable and universal insights into enhancing the efficiency of cathodes in Li-S battery.

Investigation of Hydrothermal Carbonization of Exhausted Chestnut from Tannin Extraction: Impact of Process Water Recirculation for Sustainable Fuel Production

This study explores the hydrothermal carbonization (HTC) process applied to the exhausted chestnut produced by the tannin extraction industry, utilizing process water recirculation to enhance the efficiency and sustainability of the conversion process. Tannin extraction from wood typically involves hot water treatment, leaving behind residual wood biomass known as exhausted wood. These by-products maintain their renewable properties because they have only been exposed to hot water under a high pressure, which is unlikely to cause major alterations in their structural components. Hydrothermal treatment was carried out at temperatures of 220 °C and 270 °C for 1 h, with process water being recirculated four times. This investigation focused on analyzing the effects of recirculation on the yield and fuel properties of hydrochar, as well as characterizing the combustion behavior of the obtained hydrochar. The results indicated that recirculation of process water led to improvements in both the mass and energy yields of hydrochar. The mass yield of the hydrochar samples increased by 5–6%, and the ERE of the hydrochar samples increased by 5–8% compared to the HTC reference sample. However, alterations in the combustion characteristics were observed, including decreases in ignition temperature and combustion reactivity. The results indicate that, with PW recirculations, the combustion index decreased by about 14% and 18% for 220 °C and 270 °C, respectively. Overall, this research demonstrates the potential of utilizing HTC on chestnut tannin residue with process water recirculation to produce stable solid fuel and provides insights into the combustion behavior of the resulting hydrochar.

Green hydrogen vs green ammonia: A hierarchical optimization-based integrated temporal approach for comparative techno-economic analysis of international supply chains

Recent global trends have increasingly focused on sustainable and green energy solutions,transitioning away from fossil fuels. Green hydrogen (GH) and green ammonia (GA) have emerged as promising contenders for energy carriers in international supply chains. Our manuscript delivers a thorough comparative analysis of GH and GA, acknowledging the complex interrelations among synthesis, storage, distribution, and conversion processes. This evaluation also incorporates the variability of weather, energy demand, and the delays inherent in shipping, on both hourly and seasonal scales. The study features a detailed case analysis of nine international trading routes, utilizing a hierarchical optimization framework and conducting comparative economic evaluations. Additionally, the study delves into a sensitivity analysis, exploring factors such as economies of scale and the operational constraints of water electrolyzer. One of the key findings of our research is the identification of GA as a more favorable option for an international energy carrier, particularly when considering renewable energy's seasonality and intermittency. GA's superior storage and transportation properties significantly mitigate uncertainties within the supply chain, offering a more robust solution in the context of green energy transportation and logistics. Furthermore, the techno-economic analyses survey their impact on each supply chain and reveal the interconnectedness between each supply chain element – power, conversion, storage, and transportation.

Multifold enhancement of quantum SNR by using an EMCCD as a photon number resolving device

Electron multiplying charge-coupled devices (EMCCDs), owing to their high quantum efficiency and spatial resolution, are widely used to study typical quantum optical phenomena and related applications. Researchers have already developed a procedure that enables one to statistically determine whether a pixel detects a single photon, based on whether its output is higher or lower than the estimated noise level. However, these techniques are feasible at extremely low photon numbers (≈0.15 mean number of photons per pixel per exposure), allowing for at most one photon per pixel. This limitation necessitates a very large number of frames required for any study. In this work, we present a method to estimate the mean rate of photons per pixel per frame for arbitrary exposure time. Subsequently, we make a statistical estimate of the number of photons (≥ 1) incident on each pixel. This allows us to effectively use the EMCCD as a photon number resolving device. This immediately augments the acceptable light levels in the experiments, leading to significant reduction in the required experimentation time. As evidence of our approach, we quantify contrast in quantum correlation exhibited by a pair of spatially entangled photons generated by a spontaneous parametric down conversion process. In comparison with conventional methods, our method realizes an enhancement in the signal-to-noise ratio (SNR) by approximately a factor of 3 for half the data collection time. This SNR can be easily enhanced by minor modifications in experimental parameters such as exposure time, etc.

Identifying the key structural features of Ni-based catalysts for the CO2 methanation reaction

Identifying the parameters influencing the selectivity of products is prominently significant for fabricating efficient catalysts. However, little progress has been made in describing the regulation rule of CH4 selectivity toward the CO2 methanation reaction, which is considered a vital process for CO2 emission and conversion. Herein, we disclosed the integral role of the electronegativity of M atoms in Ni-MOx supported catalysts to producing CH4 molecules, which the satisfactory catalytic performance stemmed from the regulated ability to capture CO2 molecules and CO intermediates. More importantly, alongside the extensively studied descriptor of particle size, we uncovered a strong correlation between the electronegativity of M atom and CH4 selectivity, in which the CO/CO2 adsorption capacity upon the Ni/NiOx/MOx interfaces exhibited a volcanic trend based on the electronegativity of M atoms in MOx supports. The screened Ni-Y2O3 composite catalysts demonstrated excellent CO2 methanation performance, suggesting the powerful practicability of the electronegativity of M atoms in MOx supports as a descriptor. These findings not only shed fundamental insight into the reaction pathway but also paved the way for the rational design of Ni-based catalysts based on the simple descriptor of electronegativity.

Plasmon-Induced Hot Electrons in Nanostructured Materials: Generation, Collection, and Application to Photochemistry.

Plasmon refers to the coherent oscillation of all conduction-band electrons in a nanostructure made of a metal or a heavily doped semiconductor. Upon excitation, the plasmon can decay through different channels, including nonradiative Landau damping for the generation of plasmon-induced energetic carriers, the so-called hot electrons and holes. The energetic carriers can be collected by transferring to a functional material situated next to the plasmonic component in a hybrid configuration to facilitate a range of photochemical processes for energy or chemical conversion. This article centers on the recent advancement in generating and utilizing plasmon-induced hot electrons in a rich variety of hybrid nanostructures. After a brief introduction to the fundamentals of hot-electron generation and decay in plasmonic nanocrystals, we extensively discuss how to collect the hot electrons with various types of functional materials. With a focus on plasmonic nanocrystals made of metals, we also briefly examine those based upon heavily doped semiconductors. Finally, we illustrate how site-selected growth can be leveraged for the rational fabrication of different types of hybrid nanostructures, with an emphasis on the parameters that can be experimentally controlled to tailor the properties for various applications.

The Role of Transition Metal Versus Coordination Mode in Single-Atom Catalyst for Electrocatalytic Sulfur Reduction Reaction.

Electrocatalytic sulfur reduction reaction (SRR) is emerging as an effective strategy to combat the polysulfide shuttling effect, which remains a critical factor impeding the practical application of the Li-S battery. Single-atom catalyst (SAC), one of the most studied catalytic materials, has shown considerable potential in addressing the polysulfide shuttling effect in a Li-S battery. However, the role played by transition metal vs coordination mode in electrocatalytic SRR is trial-and-error, and the general understanding that guides the synthesis of the specific SAC with desired property remains elusive. Herein, we use first-principles calculations and machine learning to screen a comprehensive data set of graphene-based SACs with different transition metals, heteroatom doping, and coordination modes. The results reveal that the type of transition metal plays the decisive role in SAC for electrocatalytic SRR, rather than the coordination mode. Specifically, the 3d transition metals exhibit admirable electrocatalytic SRR activity for all of the coordination modes. Compared with the reported N3C1 and N4 coordinated graphene-based SACs covering 3d, 4d, and 5d transition metals, the proposed para-MnO2C2 and para-FeN2C2 possess significant advantages on the electrocatalytic SRR, including a considerably low overpotential down to 1 mV and reduced Li2S decomposition energy barrier, both suggesting an accelerated conversion process among the polysulfides. This study may clarify some understanding of the role played by transition metal vs coordination mode for SAC materials with specific structure and desired catalytic properties toward electrocatalytic SRR and beyond.

Indexing with Excel, Part 4. Conversions 2

The first two articles in this series explained how Excel can be set up for indexing and how checks can be done using Excel. The third article gave an overview of how to transfer data from a dedicated indexing program (DIP) or an embedded indexing program like Word into Excel data. The current article examines the conversion process further by explaining how to convert an index from a digital format into Excel.

Empowering customer satisfaction chatbot using deep learning and sentiment analysis

The rapid advancement of technology holds great promise for various types of users, clients, or service providers. Intelligent robots, whether virtual or physical, can simplify the reservation process. With the development of machines and processing tools, natural language processing (NLP) and natural language understanding (NLU) have emerged to help people comprehend spoken language through machines. In order to facilitate seamless human-machine interaction, we aim to address customer needs through a chatbot. The objective of this paper is to incorporate sentiment analysis techniques with deep learning algorithms to cater to customers’ needs during message exchanges. This study aims to create an intelligent chatbot to engage customers during their routine operations and offer support. In addition, it offers to companies a manner to detect sarcastic messages. The proposed chatbot utilizes deep learning techniques to predict users’ intentions based on the questions asked and provide a helpful and convenient answer. A new chatbot for the customer is presented to overcome with challenges related to a wrong statement like sarcastic one and feedback towards user messages. A comparison between deep and transfer learning gives a new insight to include sentiments and sarcasm detection in the conversion process.