尿素生产技术进展评述

介绍了目前先进的尿素生产技术,评述了各工艺的主要特点与新技术进展。     

State‐of‐the‐art: software inspections after 25 years

Software inspections, which were originally developed by Michael Fagan in 1976, are an important means to verify and achieve sufficient quality in many software projects today. Since Fagan's initial work, the importance of software inspections has been long recognized by software developers and many organizations. Various proposals have been made by researchers in the hope of improving Fagan's inspection method. The proposals include structural changes to the process and several types of support for the inspection process. Most of the proposals have been empirically investigated in different studies. This is a review paper focusing on the software inspection process in the light of Fagan's inspection method and it summarizes and reviews other types of software inspection processes that have emerged in the last 25 years. This paper also addresses important issues related to the inspection process and examines experimental studies and their findings that are of interest with the purpose of identifying future avenues of research in software inspection. Copyright © 2002 John Wiley & Sons, Ltd.     

How online review environment affects review generation behavior: A competing for attention perspective

From the perspective of competing for attention, this study attempts to examine how a potential reviewer’s review content in terms of topic diversity and topic popularity is affected by the review environment, which is characterized by review volume, review variance, and time distance. The empirical analysis is based on 70,383 restaurant reviews collected from Yelp. The Latent Dirichlet Allocation (LDA) model is adopted to conduct review text mining. Our empirical findings indicate that reviewers are more likely to evaluate the product on a wider range of topics when exposed to a larger volume or lower variance of existing reviews. Our findings also show that reviewers prefer to talk about popular topics as the volume of prior reviews increases or when prior reviews exhibit higher variance, but they tend to discuss unpopular topics when time distance from the first review increases.     

Drug Usage Safety from Drug Reviews with Hybrid Machine Learning Approach

With the increasing usage of drugs to remedy different diseases, drug safety has become crucial over the past few years. Often medicine from several companies is offered for a single disease that involves the same/similar substances with slightly different formulae. Such diversification is both helpful and dangerous as such medicine proves to be more effective or shows side effects to different patients. Despite clinical trials, side effects are reported when the medicine is used by the mass public, of which several such experiences are shared on social media platforms. A system capable of analyzing such reviews could be very helpful to assist healthcare professionals and companies for evaluating the safety of drugs after it has been marketed. Sentiment analysis of drug reviews has a large potential for providing valuable insights into these cases. Therefore, this study proposes an approach to perform analysis on the drug safety reviews using lexicon-based and deep learning techniques. A dataset acquired from the ‘Drugs.Com’ containing reviews of drug-related side effects and reactions, is used for experiments. A lexicon-based approach, Textblob is used to extract the positive, negative or neutral sentiment from the review text. Review classification is achieved using a novel hybrid deep learning model of convolutional neural networks and long short-term memory (CNN-LSTM) network. The CNN is used at the first level to extract the appropriate features while LSTM is used at the second level. Several well-known machine learning models including logistic regression, random forest, decision tree, and AdaBoost are evaluated using term frequency-inverse document frequency (TF-IDF), a bag of words (BoW), feature union of (TF-IDF + BoW), and lexicon-based methods. Performance analysis with machine learning models, long short term memory and convolutional neural network models, and state-of-the-art approaches indicate that the proposed CNN-LSTM model shows superior performance with an 0.96 accuracy. We also performed a statistical significance T-test to show the significance of the proposed CNN-LSTM model in comparison with other approaches.     

Deep Learning Enabled Social Media Recommendation Based on User Comments

Nowadays, review systems have been developed with social media Recommendation systems (RS). Although research on RS social media is increasing year by year, the comprehensive literature review and classification of this RS research is limited and needs to be improved. The previous method did not find any user reviews within a time, so it gets poor accuracy and doesn’t filter the irrelevant comments efficiently. The Recursive Neural Network-based Trust Recommender System (RNN-TRS) is proposed to overcome this method’s problem. So it is efficient to analyse the trust comment and remove the irrelevant sentence appropriately. The first step is to collect the data based on the transactional reviews of social media. The second step is pre-processing using Imbalanced Collaborative Filtering (ICF) to remove the null values from the dataset. Extract the features from the pre-processing step using the Maximum Support Grade Scale (MSGS) to extract the maximum number of scaling features in the dataset and grade the weights (length, count, etc.). In the Extracting features for Training and testing method before that in the feature weights evaluating the softmax activation function for calculating the average weights of the features. Finally, In the classification method, the Recursive Neural Network-based Trust Recommender System (RNN-TRS) for User reviews based on the Positive and negative scores is analysed by the system. The simulation results improve the predicting accuracy and reduce time complexity better than previous methods.     

Esports as playful consumption experiences: Examining the antecedents and consequences of game engagement

This study aims to propose and test a conceptual model identifying playful-consumption experiences (i.e., role-projection, fantasy, escapism, enjoyment, sensory experiences, emotional involvement, and arousal) as potential drivers of consumer esports videogame engagement as well as continuance intentions, electronic word-of-mouth (eWOM), and online reviews as possible outcomes. Using the esports games' context and analyzing data from 290 gamers, the study utilized PLS-SEM using SmartPLS 3.3.9 to test the structural model. The results showed that the proposed playful-consumption experiences such as enjoyment, sensory experiences, emotional involvement, and arousal positively affect consumers’ esports game engagement. Furthermore, the results indicate the positive influence of esports game engagement on continuance intentions to play esports, eWOM and post online reviews. This study extends the esports gaming literature by examining both the antecedents and consequences of esports game engagement and provides valuable theoretical and practical implications.     

Automated Spam Review Detection Using Hybrid Deep Learning on Arabic Opinions

Online reviews regarding purchasing services or products offered are the main source of users’ opinions. To gain fame or profit, generally, spam reviews are written to demote or promote certain targeted products or services. This practice is called review spamming. During the last few years, various techniques have been recommended to solve the problem of spam reviews. Previous spam detection study focuses on English reviews, with a lesser interest in other languages. Spam review detection in Arabic online sources is an innovative topic despite the vast amount of data produced. Thus, this study develops an Automated Spam Review Detection using optimal Stacked Gated Recurrent Unit (SRD-OSGRU) on Arabic Opinion Text. The presented SRD-OSGRU model mainly intends to classify Arabic reviews into two classes: spam and truthful. Initially, the presented SRD-OSGRU model follows different levels of data preprocessing to convert the actual review data into a compatible format. Next, unigram and bigram feature extractors are utilized. The SGRU model is employed in this study to identify and classify Arabic spam reviews. Since the trial-and-error adjustment of hyperparameters is a tedious process, a white shark optimizer (WSO) is utilized, boosting the detection efficiency of the SGRU model. The experimental validation of the SRD-OSGRU model is assessed under two datasets, namely DOSC dataset. An extensive comparison study pointed out the enhanced performance of the SRD-OSGRU model over other recent approaches.     

Aspect Level Songs Rating Based Upon Reviews in English

With the advancements in internet facilities, people are more inclined towards the use of online services. The service providers shelve their items for e-users. These users post their feedbacks, reviews, ratings, etc. after the use of the item. The enormous increase in these reviews has raised the need for an automated system to analyze these reviews to rate these items. Sentiment Analysis (SA) is a technique that performs such decision analysis. This research targets the ranking and rating through sentiment analysis of these reviews, on different aspects. As a case study, Songs are opted to design and test the decision model. Different aspects of songs namely music, lyrics, song, voice and video are picked. For the reason, reviews of 20 songs are scraped from YouTube, pre-processed and formed a dataset. Different machine learning algorithms—Naïve Bayes (NB), Gradient Boost Tree, Logistic Regression LR, K-Nearest Neighbors (KNN) and Artificial Neural Network (ANN) are applied. ANN performed the best with 74.99% accuracy. Results are validated using K-Fold.