Search results

Student recruitment and retention are important issues for all higher education institutions. Constant monitoring of student satisfaction levels is therefore crucial. Traditionally, students voice their opinions through official surveys organized by the universities. In addition to that, nowadays, social media and review websites such as “Rate my professors” are rich sources of opinions that should not be ignored. Automated mining of students’ opinions can be realized via aspect-based sentiment analysis (ABSA). ABSA s is a sub-discipline of natural language processing (NLP) that focusses on the identification of sentiments (negative, neutral, positive) and aspects (sentiment targets) in a sentence. The purpose of this paper is to introduce a system for ABSA of free text reviews expressed in student opinion surveys in the Serbian language. Sentiment analysis was carried out at the finest level of text granularity – the level of sentence segment (phrase and clause).

The presented system relies on NLP techniques, machine learning models, rules and dictionaries. The corpora collected and annotated for system development and evaluation comprise students’ reviews of teaching staff at the Faculty of Technical Sciences, University of Novi Sad, Serbia, and a corpus of publicly available reviews from the Serbian equivalent of the “Rate my professors” website.

The research results indicate that positive sentiment can successfully be identified with the F-measure of 0.83, while negative sentiment can be detected with the F-measure of 0.94. While the F-measure for the aspect’s range is between 0.49 and 0.89, depending on their frequency in the corpus. Furthermore, the authors have concluded that the quality of ABSA depends on the source of the reviews (official students’ surveys vs review websites).

The system for ABSA presented in this paper could improve the quality of service provided by the Serbian higher education institutions through a more effective search and summary of students’ opinions. For example, a particular educational institution could very easily find out which aspects of their service the students are not satisfied with and to which aspects of their service more attention should be directed.

To the best of the authors’ knowledge, this is the first study of ABSA carried out at the level of sentence segment for the Serbian language. The methodology and findings presented in this paper provide a much-needed bases for further work on sentiment analysis for the Serbian language that is well under-resourced and under-researched in this area.

Up to date development in sentiment analysis has resulted in a symbolic growth in the volume of study, especially on more subjective text types, namely, product or movie reviews. The key difference between these texts with news articles is that their target is defined and unique across the text. Hence, the reviews on newspaper articles can deal with three subtasks: correctly spotting the target, splitting the good and bad content from the reviews on the concerned target and evaluating different opinions provided in a detailed manner. On defining these tasks, this paper aims to implement a new sentiment analysis model for article reviews from the newspaper.

Here, tweets from various newspaper articles are taken and the sentiment analysis process is done with pre-processing, semantic word extraction, feature extraction and classification. Initially, the pre-processing phase is performed, in which different steps such as stop word removal, stemming, blank space removal are carried out and it results in producing the keywords that speak about positive, negative or neutral. Further, semantic words (similar) are extracted from the available dictionary by matching the keywords. Next, the feature extraction is done for the extracted keywords and semantic words using holoentropy to attain information statistics, which results in the attainment of maximum related information. Here, two categories of holoentropy features are extracted: joint holoentropy and cross holoentropy. These extracted features of entire keywords are finally subjected to a hybrid classifier, which merges the beneficial concepts of neural network (NN), and deep belief network (DBN). For improving the performance of sentiment classification, modification is done by inducing the idea of a modified rider optimization algorithm (ROA), so-called new steering updated ROA (NSU-ROA) into NN and DBN for weight update. Hence, the average of both improved classifiers will provide the classified sentiment as positive, negative or neutral from the reviews of newspaper articles effectively.

Three data sets were considered for experimentation. The results have shown that the developed NSU-ROA + DBN + NN attained high accuracy, which was 2.6% superior to particle swarm optimization, 3% superior to FireFly, 3.8% superior to grey wolf optimization, 5.5% superior to whale optimization algorithm and 3.2% superior to ROA-based DBN + NN from data set 1. The classification analysis has shown that the accuracy of the proposed NSU − DBN + NN was 3.4% enhanced than DBN + NN, 25% enhanced than DBN and 28.5% enhanced than NN and 32.3% enhanced than support vector machine from data set 2. Thus, the effective performance of the proposed NSU − ROA + DBN + NN on sentiment analysis of newspaper articles has been proved.

This paper adopts the latest optimization algorithm called the NSU-ROA to effectively recognize the sentiments of the newspapers with NN and DBN. This is the first work that uses NSU-ROA-based optimization for accurate identification of sentiments from newspaper articles.

As for academic papers, the customary methods for assessing the impact of books are based on citations, which is straightforward but limited to the coverage of databases. Alternative metrics can be used to avoid such limitations, such as blog citations and library holdings. However, content-level information is generally ignored, thus overlooking users’ intentions. Meanwhile, abundant academic reviews express scholars’ opinions on books, which can be used to assess books’ impact via fine-grained review mining. Hence, this study aims to assess books’ use impacts by conducting content mining of academic reviews automatically and thereby confirmed the usefulness of academic reviews to libraries and readers.

Firstly, 61,933 academic reviews in Choice: Current Reviews for Academic Libraries were collected with three metadata metrics. Then, review contents were mined to obtain content metrics. Finally, to identify the reliability of academic reviews, Choice review metrics and other assessment metrics for use impact were compared and analysed.

The analysis results reveal that fine-grained mining of academic reviews can help users quickly understand multi-dimensional features of books, judge or predict the impacts of mass books, so as to provide references for different types of users (e.g. libraries and public readers) in book selection.

Book impact assessment via content mining can provide more detail information for massive users and cover shortcomings of traditional methods. It provides a new perspective and method for researches on use impact assessment. Moreover, this study’s proposed method might also be a means by which to measure other publications besides books.

A number of crisis situations, such as natural disasters, have affected the planet over the past decade. The outcomes of such disasters are catastrophic for the infrastructures of modern societies. Furthermore, after large disasters, societies come face-to-face with important issues, such as the loss of human lives, people who are missing and the increment of the criminality rate. In many occasions, they seem unprepared to face such issues. This paper aims to present an automated social media and crowdsourcing data mining system for the synchronization of the police and law enforcement agencies for the prevention of criminal activities during and post a large crisis situation.

The paper realized qualitative research in the form of a review of the literature. This review focuses on the necessity of using social media and crowdsourcing data mining techniques in combination with advanced Web technologies for the purpose of providing solutions to problems related to criminal activities caused during and after a crisis. The paper presents the ATHENA crisis management system, which uses a number of data mining techniques to collect and analyze crisis-related data from social media for the purpose of crime prevention.

Conclusions are drawn on the significance of social media and crowdsourcing data mining techniques for the resolution of problems related to large crisis situations with emphasis to the ATHENA system.

The paper shows how the integrated use of social media and data mining algorithms can contribute in the resolution of problems that are developed during and after a large crisis.

The purpose of this paper is to address the challenge of opinion mining in text documents to perform further analysis such as community detection and consistency control. More specifically, we aim to identify and extract opinions from natural language documents and to represent them in a structured manner to identify communities of opinion holders based on their common opinions. Another goal is to rapidly identify similar or contradictory opinions on a target issued by different holders.

For the opinion extraction problem we opted for a supervised approach focusing on the feature selection problem to improve our classification results. On the community detection problem, we rely on the Infomap community detection algorithm and the multi-scale community detection framework used on a graph representation based on the available opinions and social data.

The classification performance in terms of precision and recall was significantly improved by adding a set of “meta-features” based on grouping rules of certain part of speech (POS) instead of the actual words. Concerning the evaluation of the community detection feature, we have used two quality metrics: the network modularity and the normalized mutual information (NMI). We evaluated seven one-target similarity functions and ten multi-target aggregation functions and concluded that linear functions perform poorly for data sets with multiple targets, while functions that calculate the average similarity have greater resilience to noise.

Although our solution relies on existing approaches, we managed to adapt and integrate them in an efficient manner. Based on the initial experimental results obtained, we managed to integrate original enhancements to improve the performance of the obtained results.

This paper aims to explore the relationships between website quality – through consumer-generated media stimuli-, emotions and consumer-brand engagement in online environments.

Two independent studies are conducted to examine these relationships. Study 1, based on a sample of 366 respondents, uses a structural equation modelling approach to test the research hypotheses. Study 2, based on 1,454 online consumer reviews, uses text-mining technique to examine further the relationship between emotions and consumer-brand engagement.

The findings show that all the consumer-generated media stimuli are positively related to the dimensions of emotions. However, only pleasure and arousal are positively related to the three variables of consumer-brand engagement. The findings also show cognitive processing as the strongest dimension of consumer-brand engagement providing positive sentiments towards brands.

The findings provide marketers with an understanding of how valid, useful and relevant content (i.e. information/content) creates a greater emotional connection and drive consumer-brand engagement. Marketers should be aware that consumer-generated media stimuli influence consumers’ emotions and their reaction.

This study is one of the firsts to adapt and apply the S-O-R framework in explaining online consumer-brand engagement. This study also adds to the brand engagement literature as the first study that combines PLS-SEM approach with text-mining analysis to provide a better understanding of these relationships.

Sentiment identification of Chinese text faces many challenges, such as requiring complex preprocessing steps, preparing various word dictionaries carefully and dealing with a lot of informal expressions, which lead to high computational complexity.

A method based on Chinese characters instead of words is proposed. This method represents the text into a fixed length vector and introduces the chi-square statistic to measure the categorical sentiment score of a Chinese character. Based on these, the sentiment identification could be accomplished through four main steps.

Experiments on corpus with various themes indicate that the performance of proposed method is a little bit worse than existing Chinese words-based methods on most texts, but with improved performance on short and informal texts. Especially, the computation complexity of the proposed method is far better than words-based methods.

The proposed method exploits the property of Chinese characters being a linguistic unit with semantic information. Contrasting to word-based methods, the computational efficiency of this method is significantly improved at slight loss of accuracy. It is more sententious and cuts off the problems resulted from preparing predefined dictionaries and various data preprocessing.

This study aims to conduct a systematic review and critically analyze the sentiment analysis literature in hospitality and tourism from methodological (data sets and analyzes) and thematic (topics, theories, key constructs and their relationships) perspectives.

Qualitative thematic review and quantitative systematic review were performed on 70 papers obtained from hospitality and tourism categories of two databases, namely, Web of Science and Scopus.

A total of 5 topics and 27 sub-topics were identified and the major theme is market intelligence. Sentiment variables were investigated not only as independent but also as dependent variables. The customer rating is the most investigated dependent variable, whereas moderators and mediators were rarely tested. Most reviewed studies did not use theory. The findings from the methodological review show that analysis of big data was rare. Moreover, testing the performance of sentiment analyzes was uncommon, and only one paper tested the performance of aspect/feature extraction.

This study extends prior review studies by providing a comprehensive view of how knowledge and methodologies of sentiment analysis have developed. The identified themes and key constructs serve as a solid base for future knowledge advancement. Future research directions on sentiment analysis are also provided.

To the best of the authors’ knowledge, this study is the first comprehensive methodological and thematic review of sentiment analysis in hospitality and tourism. Based on the identified findings, the authors propose several directions for future research.

With the fierce competition in the cold chain logistics market, achieving and maintaining excellent customer satisfaction is the key to an enterprise's ability to stand out. This research aims to determine the factors that affect customer satisfaction in cold chain logistics, which helps cold chain logistics enterprises identify the main aspects of the problem. Further, the suggestions are provided for cold chain logistics enterprises to improve customer satisfaction.

This research uses the text mining approach, including topic modeling and sentiment analysis, to analyze the information implicit in customer-generated reviews. First, latent Dirichlet allocation (LDA) model is used to identify the topics that customers focus on. Furthermore, to explore the sentiment polarity of different topics, bi-directional long short-term memory (Bi-LSTM), a type of deep learning model, is adopted to quantify the sentiment score. Last, regression analysis is performed to identify the significant factors that affect positive, neutral and negative sentiment.

The results show that eight topics that customer focus are determined, namely, speed, price, cold chain transportation, package, quality, error handling, service staff and logistics information. Among them, speed, price, transportation and product quality significantly affect customer positive sentiment, and error handling and service staff are significant factors affecting customer neutral and negative sentiment, respectively.

The data of the customer-generated reviews in this research are in Chinese. In the future, multi-lingual research can be conducted to obtain more comprehensive insights.

Prior studies on customer satisfaction in cold chain logistics predominantly used questionnaire method, and the disadvantage of which is that interviewees may fill out the questionnaire arbitrarily, which leads to inaccurate data. For this reason, it is more scientific to discover customer satisfaction from real behavioral data. In response, customer-generated reviews that reflect true emotions are used as the data source for this research.

Comparative opinions widely exist in online reviews as a common way of expressing consumers’ ideas or preferences toward certain products. Such opinion-rich texts are key proxies for detecting product competitiveness. The purpose of this paper is to set up a model for competitiveness analysis by identifying comparative relations from online reviews for restaurants based on both pattern matching and machine learning.

The authors define the sub-category of comparative sentences according to Chinese linguistics. Classification rules are set up for each type of comparative relations through class sequence rule. To improve the accuracy of classification, a comparative entity dictionary is then introduced for further identifying comparative sentences. Finally, the authors collect reviews for restaurants from Dianping.com to conduct experiments for testing the proposed model.

The experiments show that the proposed method outperforms the baseline methods in terms of precision in identifying comparative sentences. On the basis of such comparison-rich sentences, product features and comparative relations are extracted for sentiment analysis, and sentimental score is assigned to each comparative relation to facilitate competitiveness analysis.

Only the explicit comparative relations are discussed, neglecting the implicit ones. Besides that, the study is grounded in the assumption that all features are homogeneous. In some cases, however, the weights to different aspects are not of the same importance to market.

On the basis of comparative relation mining, product features and comparative opinions are extracted for competitiveness analysis, which is of interest to businesses for finding weakness or strength of products, as well as to consumers for making better purchase decisions.

Comparative relation mining could be possibly applied in social media for identifying relations among users or products, and ranking users or products, as well as helping companies target and track competitors to enhance competitiveness.

The authors propose a research framework for restaurant competitiveness analysis by mining comparative relations from online consumer reviews. The results would be able to differentiate one restaurant from another in some aspects of interest to consumers, and reveal the changes in these differences over time.