Aspect Mining Research Articles

Discovery of smart hotels’ competitiveness based on online reviews

The rapid expansion of smart hotels in recent years has aroused researchers' interest in their competitiveness. While previous research has identified factors influencing the competitiveness of smart hotels, little effort has been devoted to understanding the specific competitive strengths and weaknesses of individual smart hotels. This study addresses the research gap by proposing a novel artificial intelligence framework that analyzes the competitive strengths and weaknesses of smart hotels based on online review data. The framework employs aspect-level sentiment analysis, outlying aspect mining, and theory of lodging to identify detailed competitive strengths and weaknesses of smart hotels from different perspectives. The effectiveness of the proposed framework is demonstrated through a case study of major smart hotels worldwide. The results extend the theory of lodging by incorporating new factors related to smart hotels and provide valuable insights that can help smart hotel practitioners develop strategies to enhance competitiveness at the firm, brand, and market levels.

A hybrid model for aspect-based sentiment analysis on customer feedback: research on the mobile commerce sector in Vietnam

Feedback and comments on mobile commerce applications are extremely useful and valuable information sources that reflect the quality of products or services to determine whether data is positive or negative and help businesses monitor brand and product sentiment in customers’ feedback and understand customers’ needs. However, the increasing number of comments makes it increasingly difficult to understand customers using manual methods. To solve this problem, this study builds a hybrid research model based on aspect mining and comment classification for aspect-based sentiment analysis (ABSA) to deeply comprehend the customer and their experiences. Based on previous classification results, we first construct a dictionary of positive and negative words in the e-commerce field. Then, the POS tagging technique is applied for word classification in Vietnamese to extract aspects of model commerce related to positive or negative words. The model is implemented with machine and deep learning methods on a corpus comprising more than 1,000,000 customer opinions collected from Vietnam's four largest mobile commerce applications. Experimental results show that the Bi-LSTM method has the highest accuracy with 92.01%; it is selected for the proposed model to analyze the viewpoint of words on real data. The findings are that the proposed hybrid model can be applied to monitor online customer experience in real time, enable administrators to make timely and accurate decisions, and improve the quality of products and services to take a competitive advantage.

Detection and explanation of anomalies in healthcare data

The growth of databases in the healthcare domain opens multiple doors for machine learning and artificial intelligence technology. Many medical devices are available in the medical field; however, medical errors remain a severe challenge. Different algorithms are developed to identify and solve medical errors, such as detecting anomalous readings, anomalous health conditions of a patient, etc. However, they fail to answer why those entries are considered an anomaly. This research gap leads to an outlying aspect mining problem. The problem of outlying aspect mining aims to discover the set of features (a.k.a subspace) in which the given data point is dramatically different than others. In this paper, we present a framework that detects anomalies in healthcare data and then provides an explanation of anomalies. This paper aims to effectively and efficiently detect anomalies and explain why they are considered anomalies by detecting outlying aspects. First, we re-introduced four anomaly detection techniques and outlying aspect mining algorithms. Then, we evaluate the performance of anomaly detection techniques and choose the best anomaly detection algorithm. Later, we detect the top k anomaly as a query and detect their outlying aspect. Lastly, we evaluate their performance on 16 real-world healthcare datasets. The experimental results show that the latest isolation-based outlying aspect mining measure, SiNNE, has outstanding performance on this task and has promising results.

What motivates customers to publish online reviews promptly? A text mining perspective

PurposeThis work aims to explore why people review their experienced online shopping in such a manner (promptness), and what is the potential relationship between the users’ review promptness and review motivation as well as reviewed contents.Design/methodology/approachTo evaluate the customers’ responses regarding their shopping experiences, in this paper, the “purchase-review” promptness is studied to explore the temporal characteristics of users’ reviewing behavior online. Then, an aspect mining method was introduced for assessment of review text. Finally, a theoretical model is proposed to analyze how the customers’ reviews were formed.FindingsFirst, the length of time elapsed between purchase and review was found to follow a power-law distribution, which characterizes an important number of human behaviors. Within online review behaviors, this meant that a high frequency population of reviewers tended to publish relatively quick reviews online. This showed that the customers’ reviewing behaviors on e-commerce websites may have been affected by extrinsic motivations, intrinsic motivations or both. Second, the proposed review-to-feature mapping technique is a feasible method for exploring reviewers’ opinions in both massive and sparse reviews. Finally, the customers’ reviewing behaviors were found to be mostly consistent with reviewers’ motivations.Originality/valueFirst, the authors propose that the “promptness” of users in posting online reviews is an important external manifestation of their motivation, product experience and service experience. Second, a semi-supervised method of review-to-aspect mapping is used to solve the data quality problem in mining information from massive text data, which vary in length, detail and quality. Finally, a huge amount of e-commerce customers’ purchase-review promptness are studied and the results indicate that not all product features are responsible for the “prompt” posting of users’ reviews, and that the platform’s strategy to encourage users to post reviews will not work in the long term.

A New Dimensionality-Unbiased Score for Efficient and Effective Outlying Aspect Mining

The main aim of the outlying aspect mining algorithm is to automatically detect the subspace(s) (a.k.a. aspect(s)), where a given data point is dramatically different than the rest of the data in each of those subspace(s) (aspect(s)). To rank the subspaces for a given data point, a scoring measure is required to compute the outlying degree of the given data in each subspace. In this paper, we introduce a new measure to compute outlying degree, called Simple Isolation score using Nearest Neighbor Ensemble (SiNNE), which not only detects the outliers but also provides an explanation on why the selected point is an outlier. SiNNE is a dimensionally unbias measure in its raw form, which means the scores produced by SiNNE are compared directly with subspaces having different dimensions. Thus, it does not require any normalization to make the score unbiased. Our experimental results on synthetic and publicly available real-world datasets revealed that (i) SiNNE produces better or at least the same results as existing scores. (ii) It improves the run time of the existing outlying aspect mining algorithm based on beam search by at least two orders of magnitude. SiNNE allows the existing outlying aspect mining algorithm to run in datasets with hundreds of thousands of instances and thousands of dimensions which was not possible before.

Pinpointing Early Signs of Impending Slope Failures From Space

AbstractA promised potential of spaceborne interferometric synthetic aperture radars (InSAR) is a capability for regularly monitoring ground deformation with millimeter accuracy, for timely forecasting of impending natural hazards such as landslides. The main limitation in InSAR being actually capable of unleashing this potential for hazard prediction is that key precursory ground displacements are, in the majority of cases, a very small subset of the entire big data set provided by the method over large regions. Consequently, pinpointing a single impending failure may become very difficult or impossible. We develop a data‐driven framework that can handle such imbalanced spatiotemporal data based on the concept of outlying aspects mining, to find a subset of features out of a collection of potential features, which best distinguishes the landslide source area from the others. We show that the identified feature subspace can be used to find anomalous areas across multiple spatial scales, such that Sentinel‐1 satellite monitoring points which persistently lie in these areas can accurately detect the location of the Xinmo landslide (China) almost 1 year in advance—without false alarms. In a second case study, we identify the area affected by rockfalls on Stromboli volcano, a task that is generally infeasible with traditional methods applied to InSAR data. With continuing improvements in the spatial and temporal resolution from the new generation of satellites, such as Sentinel‐1, this approach opens the door to reliable and early prediction of failure over a broad range of slope instabilities.

Understanding host marketing strategies on Airbnb and their impact on listing performance: a text analytics approach

PurposePeer-to-peer (P2P) accommodation sharing has become a significant part of the travel and lodging industry, allowing homeowners to engage in entrepreneurial activity via sharing of resources. However, there is limited understanding of how hosts can use listing descriptions to better match their offerings to different consumer segments. The purpose of this paper is to understand the use of listing descriptions by Airbnb hosts and the impact of such descriptions on sales performance.Design/methodology/approachIn this paper, a deep learning-based sentence-level aspect mining approach is used to extract various aspects from host-provided listing descriptions. Then a regression-based approach is used to understand the impact of various aspects of listing descriptions on listing performance.FindingsIt was found that aspects for which listing descriptions are the sole source of information have the greatest influence on listing performance. The authors also find that the impact of an aspect on listing performance varies by listing type, and that there is a mismatch between the most included aspects by hosts in their listing descriptions and the most influential aspects that impact sales.Originality/valueThe impact of consumer reviews in the context of Airbnb has been extensively studied. A novel aspect of this study is the exploration of P2P accommodations from a supplier perspective, by understanding the use and impact of host-provided textual descriptions on sales. The findings of this study can help better market properties from a practice perspective and better understand consumer information consumption from a theoretical perspective. The authors also demonstrate a new approach for exploring social phenomena by performing quantitative analysis on textual data using deep-learning and regression-based techniques.

Hybrid Collaborative Fusion Based Product Recommendation Exploiting Sentiments from Implicit and Explicit Reviews

Product recommendation is an important functionality in online ecommerce systems. The goal of the recommendation system is to recommend products with has higher purchase success ratio. User profile, product purchase history etc. have been used in many works to provide high quality recommendations. Product reviews is one of the important source for personalized recommendation. Typical collaborative recommendation systems are built upon user rating on products. But in many cases, these rating information are inaccurate or not available. There is also a problem of biased reviews decreasing the accuracy of recommendation systems. This work proposes a aspect mining collaborative fusion based recommendation system considering both the implicit and explicit reviews. The sentiments about different aspects mined from reviews are translated to multi-dimensional ratings. These ratings are then fused with user profile and demographic attributes to improve the quality of recommendation. The proposed recommendation system has 3.79% lower RMSE, 4.51% lower MAE and 22% lower MRE compared to most recent collaborative filtering based recommendation system.

Implicit Aspect-Based Opinion Mining and Analysis of Airline Industry Based on User-Generated Reviews

Mining opinions from reviews has been a field of ever-growing research. These include mining opinions on document level, sentence level and even aspect level. While explicitly mentioned aspects from user-generated texts have been widely researched, very little work has been done in gathering opinions on aspects that are implied and not explicitly mentioned. Previous work to identify implicit aspects and opinion was limited to syntactic-based classifiers or other machine learning methods trained on restaurant dataset. In this paper, the present is a novel study for extracting and analysing implicit aspects and opinions from airline reviews in English. Through this study, an airline domain-specific aspect-based annotated corpus, and a novel two-way technique that first augments pre-trained word embeddings for sequential with stochastic gradient descent optimized conditional random fields (CRF) and second using machine and ensemble learning algorithms to classify the implied aspects is devised and developed. This two-way technique resolves double-implicit problem, most encountered by previous work in implicit aspect and opinion text mining. Experiments with a hold-out test set on the first level i.e., entity extraction by optimized CRF yield a result of ROC-AUC score of 96% and F1 score of 94% outperforming few baseline systems. Further experiments with a range of machine and ensemble learning classifier algorithms to classify implied aspects and opinions for each entity yields a result of ROC-AUC score ranging from 71 to 94.8% for all implied entities. This two-level technique for implicit aspect extraction and classification outperforms many baseline systems in this domain.

SEML: A Semi-Supervised Multi-Task Learning Framework for Aspect-Based Sentiment Analysis

Aspect-Based Sentiment Analysis (ABSA) involves two sub-tasks, namely Aspect Mining (AM) and Aspect Sentiment Classification (ASC), which aims to extract the words describing aspects of a reviewed entity (e.g., a product or service) and analyze the expressed sentiments on the aspects. As AM and ASC can be formulated as a sequence labeling problem to predict the aspect or sentiment labels of each word in the review, supervised deep sequence learning models have recently achieved the best performance. However, these supervised models require a large number of labeled reviews which are very costly or unavailable, and they usually perform only one of the two sub-tasks, which limits their practical use. To this end, this paper proposes a SEmi-supervised Multi-task Learning framework (called SEML) for ABSA. SEML has three key features. (1) SEML applies Cross-View Training (CVT) to enable semi-supervised sequence learning over a small set of labeled reviews and a large set of unlabeled reviews from the same domain in a unified end-to-end architecture. (2) SEML solves the two sub-tasks simultaneously by employing three stacked bidirectional recurrent neural layers to learn the representations of reviews, in which the representations learned from different layers are fed into CVT, AM and ASC, respectively. (3) SEML develops a Moving-window Attentive Gated Recurrent Unit (MAGRU) for the three recurrent neural layers to enhance representation learning and prediction accuracy, as nearby contexts within a moving-window in a review can provide important semantic information for the prediction task in ABSA. Finally, we conduct extensive experiments on ABSA over four review datasets from the SemEval workshops. Experimental results show that SEML significantly outperforms the state-of-the-art models.

Evaluation of Software Evolution based Aspect Mining Technique

Evaluation of Software Evolution based Aspect Mining Technique

A Survey on Opinion Mining: From Stance to Product Aspect

With the prevalence of social media and online forum, opinion mining, aiming at analyzing and discovering the latent opinion in user-generated reviews on the Internet, has become a hot research topic. This survey focuses on two important subtasks in this field, stance detection and product aspect mining, both of which can be formalized as the problem of the triple (target, aspect, opinion) extraction. In this paper, we first introduce the general framework of opinion mining and describe the evaluation metrics. Then, the methodologies for stance detection on different sources, such as online forum and social media are discussed. After that, approaches for product aspect mining are categorized into three main groups which are corpus level aspect extraction, corpus level aspect, and opinion mining, and document level aspect and opinion mining based on the processing units and tasks. And then we discuss the challenges and possible solutions. Finally, we summarize the evolving trend of the reviewed methodologies and conclude the survey.

A new simple and efficient density estimator that enables fast systematic search

This paper introduces a simple and efficient density estimator that enables fast systematic search. To show its advantage over commonly used kernel density estimator, we apply it to outlying aspects mining. Outlying aspects mining discovers feature subsets (or subspaces) that describe how a query stand out from a given dataset. The task demands a systematic search of subspaces. We identify that existing outlying aspects miners are restricted to datasets with small data size and dimensions because they employ kernel density estimator, which is computationally expensive, for subspace assessments. We show that a recent outlying aspects miner can run orders of magnitude faster by simply replacing its density estimator with the proposed density estimator, enabling it to deal with large datasets with thousands of dimensions that would otherwise be impossible.

Coupled matrix factorization and topic modeling for aspect mining

Aspect mining, which aims to extract ad hoc aspects from online reviews and predict rating or opinion on each aspect, can satisfy the personalized needs for evaluation of specific aspect on product quality. Recently, with the increase of related research, how to effectively integrate rating and review information has become the key issue for addressing this problem. Considering that matrix factorization is an effective tool for rating prediction and topic modeling is widely used for review processing, it is a natural idea to combine matrix factorization and topic modeling for aspect mining (or called aspect rating prediction). However, this idea faces several challenges on how to address suitable sharing factors, scale mismatch, and dependency relation of rating and review information. In this paper, we propose a novel model to effectively integrate Matrix factorization and Topic modeling for Aspect rating prediction (MaToAsp). To overcome the above challenges and ensure the performance, MaToAsp employs items as the sharing factors to combine matrix factorization and topic modeling, and introduces an interpretive preference probability to eliminate scale mismatch. In the hybrid model, we establish a dependency relation from ratings to sentiment terms in phrases. The experiments on two real datasets including Chinese Dianping and English Tripadvisor prove that MaToAsp not only obtains reasonable aspect identification but also achieves the best aspect rating prediction performance, compared to recent representative baselines.

Scalable code clone detection and search based on adaptive prefix filtering

Code clone detection is a well-known software engineering problem that aims to detect all the groups of code blocks or code fragments that are functionally equivalent in a code base. It has numerous and wide ranging important uses in areas such as software metrics, plagiarism detection, aspect mining, copyright infringement investigation, code compaction, virus detection, and detecting bugs. A scalable code clone detection technique, able to process large source code repositories, is crucial in the context of multi-project or Internet-scale code clone detection scenarios. In this paper, we focus on improving the scalability of code clone detection, relative to current state of the art techniques. Our adaptive prefix filtering technique improves the performance of code clone detection for many common execution parameters, when tested on common benchmarks. The experimental results exhibit improvements for commonly used similarity thresholds of between 40% and 80%, in the best case decreasing the execution time up to 11% and increasing the number of filtered candidates up to 63%.

A Survey of Aspect Mining Tools and Techniques

A Survey of Aspect Mining Tools and Techniques

Software Evolution-based Aspect Mining: A Novel Approach

Aspect mining is the search of candidate aspects in existing systems and isolates them from the system into separately described aspects. The cross-cutting concerns are candidate aspects. The aspect-mining techniques that have been proposed in literature perform static or dynamic analysis of source code to identify the candidate aspect. The data-mining techniques such as clustering and association rule mining have also been applied on execution traces or in combination with source code metrics. History-based aspect mining is based on mining methods calls that have been inserted during the evolution of software. It assumes that cross-cutting concerns do not exist from beginning but are introduced over time. However, the cross-cutting concerns may exist in the system from the beginning. We have been investigating an approach to mine frequent patterns from the version histories of legacy system to recommend candidate aspects. A novel approach, Software Evolution based Aspect Mining (SEAM) software evolution-based aspect mining for mining candidate aspects from version history files is proposed in the paper. In the proposed approach, while mining aspects from legacy code, the source files that have been changed frequently and set of source code files that have been changed together frequently during the evolution of system are mined. Mined frequent change patterns are then visualised for structural relationship. On the basis of the structural relationship between the files, candidate aspects are recommended for the pattern. Two types of candidate aspects are reported – simple candidate aspects and complex candidate aspects. In this paper, algorithms are proposed for mining simple and complex candidate aspects. Overall, the paper presents a novel approach to accurately identify aspects based on co-changing files existing in version history. The identification of aspects not only gives the opportunity to rewrite the code but also has potential to enhance maintainability and reliability of system.

A Model based on Effective and Intelligent Sentiment Mining: A Review

Objectives: Due to proliferation of internet spammers post fake audit to embrace or minimization items. Objective is to purpose a model that can extract spam reviews and implicit reviews. Methods/Statistical Analysis: Most research concentrated on extracting just explicit said highlights. Extraction of certain angle like implicit and spam gives more proficient result even in rating too. Pattern discovery method are proposed to known different behaviors to discover spam review. Detection metrics could be used to score every survey. Findings: Because of absence of dialect builds in the sentence implicit verifiable viewpoint extraction a mind boggling issue. Most research concentrated on extracting just explicit said highlights. The major weakness of the methods are lack of gold-standard dataset,unable to achieve better accuracy. The framework builds time arrangement of number of surveys for every brand and recognizes spam audits from genuine assessments subsequent to distinguishing suspicious intervals. Novelty/Improvements: Before obtaining anything,we need to know conclusion of others. By headway of social websites, opinion settles on potential choice for customer. Even manufacturers can enhance the nature of their item. This proposed model also has the capacity to cover dominant part of the elements which are the deciding factors for the effectiveness of aspect mining framework.

Aspect Oriented Re-engineering of Legacy Software Using Cross-Cutting Concern Characterization and Significant Code Smells Detection

Although object-oriented programming (OOP) methodologies immensely promote reusable and well-factored decomposition of complex source code, legacy software systems often show symptoms of deteriorating design over time due to lack of maintenance. Software systems may have different business and application contexts, but most of these systems require similar maintenance mechanism of understanding, analysis and transformation. As a consequence, intensive re-engineering efforts based on the model driven approach can be effective ensuring that best practices are followed during maintenance and eventually reducing the development cost. In this paper, we suggest detailed framework of re-engineering which includes: (i) rigorous and automated source code analysis technique for identification, characterization and prioritization of most prominent and threatening design flaws in legacy software, (ii) migration of existing the code to aspect-oriented programming (AOP) code by exploiting current state of art for aspect mining mechanism and incorporating behavioral knowledge of cross-cutting concerns. To exemplify how the approach works a case study has been conducted to experimentally validate the idea and analyze the effect of process on specific software quality spectrum. An explicit analysis of prevalent work on the subject and their critical reviews are also presented to further enhance the recognition of proposed re-engineering framework.

Discovering outlying aspects in large datasets

We address the problem of outlying aspects mining: given a query object and a reference multidimensional data set, how can we discover what aspects (i.e., subsets of features or subspaces) make the query object most outlying? Outlying aspects mining can be used to explain any data point of interest, which itself might be an inlier or outlier. In this paper, we investigate several open challenges faced by existing outlying aspects mining techniques and propose novel solutions, including (a) how to design effective scoring functions that are unbiased with respect to dimensionality and yet being computationally efficient, and (b) how to efficiently search through the exponentially large search space of all possible subspaces. We formalize the concept of dimensionality unbiasedness, a desirable property of outlyingness measures. We then characterize existing scoring measures as well as our novel proposed ones in terms of efficiency, dimensionality unbiasedness and interpretability. Finally, we evaluate the effectiveness of different methods for outlying aspects discovery and demonstrate the utility of our proposed approach on both large real and synthetic data sets.