Augmenting feature model through customer preference mining by hybrid sentiment analysis

Sentiment Analysis is a method to identify, extract, and quantify people's feelings, opinions, or attitudes. The wealth of online data motivates organizations to keep tabs on customers' opinions and feelings by turning to sentiment analysis tasks. Along with the sentiment analysis, the emotion analysis of written reviews is also essential to improve customer satisfaction with restaurant service. Due to the availability of massive online data, various computerized methods are proposed in the literature to decipher text sentiments. The majority of current methods rely on machine learning, which necessitates the pre-training of large datasets and incurs substantial space and time complexity. To address this issue, we propose a novel unsupervised sentiment classification model. This study presents an unsupervised mathematical optimization framework to perform sentiment and emotion analysis of reviews. The proposed model performs two tasks. First, it identifies a review's positive and negative sentiment polarities, and second, it determines customer satisfaction as either satisfactory or unsatisfactory based on a review. The framework consists of two stages. In the first stage, each review's context, rating, and emotion scores are combined to generate performance scores. In the second stage, we apply a non-cooperative game on performance scores and achieve Nash Equilibrium. The output from this step is the deduced sentiment of the review and the customer's satisfaction feedback. The experiments were performed on two restaurant review datasets and achieved state-of-the-art results. We validated and established the significance of the results through statistical analysis. The proposed model is domain and language-independent. The proposed model ensures rational and consistent results.

To analyze public perceptions of over-the-counter (OTC) hearing aids through sentiment and thematic analysis of online consumer reviews and their changes over time. Sentiment and thematic analysis. Online reviews from third-party and product websites. All English online consumer reviews posted between 2016 and 2024 for OTC hearing aids (83 models) were recorded (n = 21,727). Sentiment analysis was performed using Valence Aware Dictionary and Sentiment Reasoner (VADER), a rule-based sentiment analysis tool incorporating natural language processing. VADER provides scores for each review ranging from -1 (most negative), 0 (neutral), to 1 (most positive). Additional thematic analysis was performed for the top 100 most positive, neutral, and negative reviews (n = 300). Overall, mean (SD) VADER sentiment score of online reviews was generally positive at 0.587 (0.411). Multivariable regression analysis showed that higher VADER scores were associated with higher-priced and behind-the-ear (BTE) type hearing aids. Although there was a significant increase in a number of reviews after the Food and Drug Administration's new establishment of the OTC hearing aid category in 2022, the mean sentiment scores slightly decreased (β =-.10, [95%CI: -0.12 to -0.09]). Thematic analysis revealed that positive sentiments highlighted the affordability and time-saving benefits of OTC hearing aids as alternatives to prescription models. Negative sentiments centered on sound quality, challenges with customer service, and inadequate amplification for those with severe hearing loss. Customers generally viewed OTC hearing aids positively, while mixed experiences were present. When used as indicated for adults with mild to moderate hearing loss, OTC hearing aids may offer a viable alternative to prescription devices, improving accessibility and affordability.

Deriving customer preferences for hotels based on aspect-level sentiment analysis of online reviews

This article presents a tailored majority voting approach for enhancing the consistency and reliability of sentiment analysis in online product reviews. The methodology addresses discrepancies in sentiment classification by leveraging sentiment labels from multiple automated tools and implementing a robust majority decision rule. This consensus-based approach significantly enhances the trustworthiness and consistency of sentiment analysis outcomes, serving as a dependable foundation for training more precise sentiment analysis models. The data labeled with our method was utilized to train deep learning models, achieving competitive accuracy with significantly less data. The findings demonstrate the effectiveness of the method in producing results comparable to commercial tools while ensuring data consistency for model training.

Needs for mass customization and economies of scale have pushed engineers to develop Software Product Lines (SPLs). SPLs are families of products sharing commonalities and exhibiting differences, built by reusing software assets abstractly represented by features. Feature models describe the constraints that link the features and allow the configuration of tailored software products. Common SPLs involve hundreds, even thousands of features, leading to billions of possible software products. As a result, testing a product line is challenging due to the enormous size of the possible products. Existing techniques focus on testing based on the product line's feature model by selecting a limited set of products to test. Being created manually or reverse-engineered, feature models are prone to errors impacting the generated test suites. In this paper, we examine ability of test suites to detect such errors. In particular, we propose two mutation operators to derive erroneous feature models (mutants) from an original feature model and assess the capability of the generated original test suite to kill the mutants. Experimentation on real feature models demonstrate that dissimilar tests suites have a higher mutant detection ability than similar ones, thus validating the relevance of similarity-driven product line testing.

Feature models are widely used for describing the variability of a software product line. A feature model contains a tree of features and a set of constraints over these features, which define valid feature combinations. In the industrial practice, large feature models containing hundreds of features and constraints are common. Furthermore, in a hierarchical product line a feature model can be related to other feature models through inter-model constraints. Due to the model size and complexity, understanding industrial feature models is a challenging task.In this paper, we describe the feature model understanding challenges reported by feature model developers at Robert Bosch GmbH. To support the developers in model understanding, we extend the idea of a feature implication graph to feature relation graph by abstracting groups of implications to feature relations. A transitively closed relation graph shows all modeled and implicit feature relations and spans all related feature models. The graph is also used to identify modeling problems, such as false optional or dead features, and to show the derivation of any implicit relation or problem from the modeled constraints. In a case study at Bosch, we evaluate the use of feature relation graph for model understanding. We propose further use cases of the graph, supporting model maintenance, evolution and configuration.

Software product line engineering (SPLE) is a paradigm to promote systematic software reuse. A Feature Model (FM) is a common means to illustrate the commonality and variability of software products in a family. In most existing FM extraction approaches, keywords in the requirement document or certain types of system behavior or external events are considered features. The resulting FM is a combination of user activities and system actions (SAs), making it hard to understand. In this paper, we present an automatic approach to generate a product line FM from multiple requirement documents. We consider user activity and SAs separately in our approach and focus on the expected behaviors of the software system, together with the data being processed. The resulting FM clearly illustrates the expected functionalities of the software system and their variability in the product line. We also compared our approach with existing techniques by processing the same textual documents, and noted improvements in our results.

Trusted Product Lines

For the development of variable systems, software product lines (SPL) are an established way to handle the variability by using feature models. Nevertheless, the configuration of an SPL can be complex, especially if a product line consists of a large number of features. The problem of handling the complexity becomes even more sophisticated if not only software, but also mechatronic systems containing software and hardware components are configured. Besides modeling the software, within a mechatronic system dependencies and associations between software and hardware features need to be considered which further increases the complexity. To handle this complexity in product lines for mechatronic systems, we propose a multi product line (MPL) approach which allows to distinguish between software and hardware by using different feature models for each. In addition we introduce a level of abstraction to complex product lines consisting of multiple feature models by establishing a feature model mapping. In this paper we present details to the mapping to provide an abstract configuration view as well as the introduced associations for our MPL approach.

Feature modeling is an important approach to capture the commonalities and variabilities in system families and product lines. Cardinality‐based feature modeling integrates a number of existing extensions of the original feature‐modeling notation from Feature‐Oriented Domain Analysis. Staged configuration is a process that allows the incremental configuration of cardinality‐based feature models. It can be achieved by performing a step‐wise specialization of the feature model. In this article, we argue that cardinality‐based feature models can be interpreted as a special class of context‐free grammars. We make this precise by specifying a translation from a feature model into a context‐free grammar. Consequently, we provide a semantic interpretation for cardinality‐based feature models by assigning an appropriate semantics to the language recognized by the corresponding grammar. Finally, we give an account on how feature model specialization can be formalized as transformations on the grammar equivalent of feature models. Copyright © 2005 John Wiley & Sons, Ltd.

Product line software engineering (PLSE) is an emerging software engineering paradigm, which guides organizations toward the development of products from core assets rather than the development of products one by one from scratch. In order to develop highly reusable core assets, PLSE must have the ability to exploit commonality and manage variability among products from a domain perspective. Feature modeling is one of the most popular domain analysis techniques, which analyzes commonality and variability in a domain to develop highly reusable core assets for a product line. Various attempts have been made to extend and apply it to the development of software product lines. However, feature modeling can be difficult and time-consuming without a precise understanding of the goals of feature modeling and the aid of practical guidelines. In this paper, we clarify the concept of features and the goals of feature modeling, and provide practical guidelines for successful product line software engineering. The authors have extensively used feature modeling in several industrial product line projects and the guidelines described in this paper are based on these experiences.

Big volume of product online reviews are generated from time to time, which contain rich information regarding customer requirements. These reviews help designers to make exhaustive analyses of competitors, which is one indispensable step in market-driven product design. How to extract critical opinionate sentences associated with some specific features from product online reviews has been investigated by some researchers. However, few of them examined how to select a small number of representative yet comparative sentences for competitor analysis. In this research, a framework is illustrated to select pairs of opinionate sentences referring to a specific feature from reviews of competitive products. With the help of the techniques on sentiment analysis, opinionate sentences referring to a specific feature are first identified from product online reviews. Then, for the selection of a small number of representative yet comparative opinionate sentences, information representativeness, information comparativeness and information diversity are investigated. Accordingly, an optimization problem is formulated, and three greedy algorithms are proposed to analyze this problem for suboptimal solutions. Finally, with a large amount of real data from Amazon.com, categories of extensive experiments are conducted and the final encouraging results are realized, which prove the effectiveness of the proposed approach.

Identifying comparative customer requirements from product online reviews for competitor analysis

Feature models are frequently used to capture the knowledge about configurable software systems and product lines. However, feature modeling of large-scale systems is challenging as many models are needed for diverse purposes. For instance, feature models can be used to reflect the perspectives of product management, technical solution architecture, or product configuration. Furthermore, models are required at different levels of granularity. Although numerous approaches and tools are available, it remains hard to define the purpose, scope, and granularity of feature models. In this paper we thus present experiences of developing feature models for two large-scale industrial automation software systems. Specifically, we extended an existing feature modeling tool to support models for different purposes and at multiple levels. We report results on the characteristics and modularity of the feature models, including metrics about model dependencies. We further discuss lessons learned during the modeling process.

Among the most essential NLP applications is sentiment analysis, often known as opinion mining. In recent years, sentiment analysis has received a lot of attention. It is concerned with text classification in order to establish the intent of the text’s final user. End-user feedback becomes the most important factor in determining the quality of a product’s content. Online product reviews are regarded as one of the most important sources of customer feedback. In the current environment, people may discover on products and make selections based on online review sites. Hence, extracting the precise product reviews from the dataset wherein we have preprocessed the dataset using sentimental analysis, counter vectorizer is used for feature extraction in bag of words and the classification is done through SVM, KNN, RF, DT, NB to predict the review status whether it is positive, negative, or neutral. The model is tuned with grid search, and the confusion matrix is plotted for the above-mentioned algorithms. The final aim of the work is to provide users with their wanted products. Thus, we have tested our categorization approach through amazon reviews.KeywordsNLPSentimental analysisOpinion miningCounter vectorizerFeature extractionGrid searchAmazon reviews