Dynamical mining of ever-changing user requirements: A product design and improvement perspective

Previous studies carried out customer surveys by questionnaires to collect data for analyzing consumer requirements. In recent years, a large and growing body of literature has investigated the extraction of customer requirements and preferences from online reviews. However, since customer requirements change dynamically over time, traditional studies failed to obtain the change data of customer requirements and opinions based on sentiments expressed in reviews. In this paper, a new method for dynamically mining user requirements is proposed, which is used to analyze the changing behavior of product attributes and improve product design. Dynamic mining differs from the traditional need acquisition mainly in three aspects: (1) it involves dynamically mining user requirements over time (2) it adds changes in manufacturers’ opinions to the analysis (3) it allows for product improvement strategies based on the changing behavior of product attributes. First, text mining is adopted to collect customer and manufacturer review data for different time periods and extract product attributes. A Natural Language Processing tool is used to measure the importance weight and sentiment score of product attributes. Second, an approach for dynamically mining user requirements is introduced to classify product attributes and analyze the changes of attribute data in three categories over time. Finally, an improvement strategy for next-generation product design is developed based on the changing behavior of attributes. Moreover, a case study on vehicles based on online reviews was conducted to illustrate the proposed methodology. Our research suggests that the proposed approach can accurately mine customer requirements and lead to successful product improvement strategies for next-generation products.     

DENFIS: dynamic evolving neural-fuzzy inference system and itsapplication for time-series prediction

This paper introduces a new type of fuzzy inference systems, denoted as dynamic evolving neural-fuzzy inference system (DENFIS), for adaptive online and offline learning, and their application for dynamic time series prediction. DENFIS evolve through incremental, hybrid (supervised/unsupervised), learning, and accommodate new input data, including new features, new classes, etc., through local element tuning. New fuzzy rules are created and updated during the operation of the system. At each time moment, the output of DENFIS is calculated through a fuzzy inference system based on m-most activated fuzzy rules which are dynamically chosen from a fuzzy rule set. Two approaches are proposed: (1) dynamic creation of a first-order Takagi-Sugeno-type fuzzy rule set for a DENFIS online model; and (2) creation of a first-order Takagi-Sugeno-type fuzzy rule set, or an expanded high-order one, for a DENFIS offline model. A set of fuzzy rules can be inserted into DENFIS before or during its learning process. Fuzzy rules can also be extracted during or after the learning process. An evolving clustering method (ECM), which is employed in both online and offline DENFIS models, is also introduced. It is demonstrated that DENFIS can effectively learn complex temporal sequences in an adaptive way and outperform some well-known, existing models     

Numerical study on the feasibility of dynamic evolving neural-fuzzy inference system for approximation of compressive strength of dry-cast concrete

This paper assesses effectiveness of dynamic evolving neural-fuzzy inference system (DENFIS) models in predicting the compressive strength of dry-cast concretes, and compares their prediction performances with those of regression, neural network (NN) and ANFIS models. The results of this study emphasized capabilities of online first-order and offline high-order Takagi–Sugeno (TSK) type DENFIS models for prediction purposes, whereas offline first-order TSK-type DENFIS models did not produce reliable results. Comparison between the produced results of an elite high-order DENFIS model with those predicted by the selected NN, regression and ANFIS models showed effectiveness of DENFIS model than the regression model, while its performance was similar to or slightly better than the other artificial prediction tools.     

中文网络评论的IT产品特征挖掘及情感倾向分析

为探索中文客户评论中的IT产品特征及相关情感倾向的挖掘,帮助IT生产商和服务商提高改进产品和服务质量,提高竞争力。该文将采用情感分析技术,提出基于客户感知价值的产品特征挖掘算法,实现对于评论中IT产品特征及其情感倾向的语义分析、动态提取和综合信息挖掘;并根据用户的关注权重将产品特征和情感倾向进行排列。采用从互联网下载的真实IT产品评论语料中进行实验,初步验证了该方法的有效性。     

Modeling customer satisfaction for new product development using a PSO-based ANFIS approach

When developing new products, it is important to understand customer perception towards consumer products. It is because the success of new products is heavily dependent on the associated customer satisfaction level. If customers are satisfied with a new product, the chance of the product being successful in marketplaces would be higher. Various approaches have been attempted to model the relationship between customer satisfaction and design attributes of products. In this paper, a particle swarm optimization (PSO) based ANFIS approach to modeling customer satisfaction is proposed for improving the modeling accuracy. In the approach, PSO is employed to determine the parameters of an ANFIS from which better customer satisfaction models in terms of modeling accuracy can be generated. A notebook computer design is used as an example to illustrate the approach. To evaluate the effectiveness of the proposed approach, modeling results based on the proposed approach are compared with those based on the fuzzy regression (FR), ANFIS and genetic algorithm (GA)-based ANFIS approaches. The comparisons indicate that the proposed approach can effectively generate customer satisfaction models and that their modeling results outperform those based on the other three methods in terms of mean absolute errors and variance of errors.     

Rough set and PSO-based ANFIS approaches to modeling customer satisfaction for affective product design

Facing fierce competition in marketplaces, companies try to determine the optimal settings of design attribute of new products from which the best customer satisfaction can be obtained. To determine the settings, customer satisfaction models relating affective responses of customers to design attributes have to be first developed. Adaptive neuro-fuzzy inference systems (ANFIS) was attempted in previous research and shown to be an effective approach to address the fuzziness of survey data and nonlinearity in modeling customer satisfaction for affective design. However, ANFIS is incapable of modeling the relationships that involve a number of inputs which may cause the failure of the training process of ANFIS and lead to the ‘out of memory’ error. To overcome the limitation, in this paper, rough set (RS) and particle swarm optimization (PSO) based-ANFIS approaches are proposed to model customer satisfaction for affective design and further improve the modeling accuracy. In the approaches, the RS theory is adopted to extract significant design attributes as the inputs of ANFIS and PSO is employed to determine the parameter settings of an ANFIS from which explicit customer satisfaction models with better modeling accuracy can be generated. A case study of affective design of mobile phones is used to illustrate the proposed approaches. The modeling results based on the proposed approaches are compared with those based on ANFIS, fuzzy least-squares regression (FLSR), fuzzy regression (FR), and genetic programming-based fuzzy regression (GP-FR). Results of the training and validation tests show that the proposed approaches perform better than the others in terms of training and validation errors.     

Sentiment analysis from Customer-generated online videos on product review using topic modeling and Multi-attention BLSTM

With the popularity of social websites and mobile applications including Instagram, YouTube, TikTok, etc., online videos shared by customers presenting their thoughts and reviews on products are posted daily in increasing numbers. Such online videos containing Voice of Customer (VOC) are precious for product designers or managers to capture customer sentiment and understand customer preference. For this purpose, we propose a novel method for analyzing customer sentiment from online videos on product review. Firstly, latent Dirichlet allocation (LDA) modeling is applied to identify the topics from the online videos after data preprocessing. Then sentiment polarity corresponding to each topic of each speaker in videos can be identified using our newly designed multi-attention bi-directional LSTM (BLSTM(MA)), which can better mine complex relationships among a speaker’s sentiments on different topics. This paper is of great practical value for company managers and researchers to better understand a large number of customer opinions on specific products. To explain the application of this method and prove its effectiveness, two cases respectively on smartphones and several published datasets are developed finally.     

Stock Trading Using RSPOP: A Novel Rough Set-Based Neuro-Fuzzy Approach

This paper investigates the method of forecasting stock price difference on artificially generated price series data using neuro-fuzzy systems and neural networks. As trading profits is more important to an investor than statistical performance, this paper proposes a novel rough set-based neuro-fuzzy stock trading decision model called stock trading using rough set-based pseudo outer-product (RSPOP) which synergizes the price difference forecast method with a forecast bottleneck free trading decision model. The proposed stock trading with forecast model uses the pseudo outer-product based fuzzy neural network using the compositional rule of inference [POPFNN-CRI(S)] with fuzzy rules identified using the RSPOP algorithm as the underlying predictor model and simple moving average trading rules in the stock trading decision model. Experimental results using the proposed stock trading with RSPOP forecast model on real world stock market data are presented. Trading profits in terms of portfolio end values obtained are benchmarked against stock trading with dynamic evolving neural-fuzzy inference system (DENFIS) forecast model, the stock trading without forecast model and the stock trading with ideal forecast model. Experimental results showed that the proposed model identified rules with greater interpretability and yielded significantly higher profits than the stock trading with DENFIS forecast model and the stock trading without forecast model.     

A novel approach for ANFIS modelling based on full factorial design

Adaptive neural network based fuzzy inference system (ANFIS) is an intelligent neuro-fuzzy technique used for modelling and control of ill-defined and uncertain systems. ANFIS is based on the input–output data pairs of the system under consideration. The size of the input–output data set is very crucial when the data available is very less and the generation of data is a costly affair. Under such circumstances, optimization in the number of data used for learning is of prime concern. In this paper, we have proposed an ANFIS based system modelling where the number of data pairs employed for training is minimized by application of an engineering statistical technique called full factorial design. Our proposed method is experimentally validated by applying it to the benchmark Box and Jenkins gas furnace data and a data set collected from a thermal power plant of the North Eastern Electric Power Corporation (NEEPCO) Limited. By employing our proposed method the number of data required for learning in the ANFIS network could be significantly reduced and thereby computation time as well as computation complexity is remarkably reduced. The results obtained by applying our proposed method are compared with those obtained by using conventional ANFIS network. It was found that our model compares favourably well with conventional ANFIS model.     

The determinants of online customer ratings: a combined domain ontology and topic text analytics approach

Merchants, as well as customers, have noticed the importance of online product reviews and numeric ratings in electronic commerce websites. It is valuable if merchants can discover some potential customer value from the sheer volume of data. This paper contributes a semantic text analytics approach that can dig out the customers’ most basic concerns about their online purchase choices. More specifically, based on the hypothesis that the product reviews and overall ratings estimated by same person in a tiny time interval have a great relevance, we dexterously utilize this relevance to realize the embedded customer value. In the proposed method, take the single lens reflex camera for example, an innovative aspect extraction method that comprehensively considers the product ontology and results of the topic modeling method latent Dirichlet allocation is applied. As a result, 8 specific aspects are identified from the experimental results. For each aspect, a self-contained review feature corpus is created as an extension of some seed terms. After aspect-based sentence segmentation and context-sensitive sentiments preprocessing, aspect-oriented sentiment analysis is applied. Multiple regression analysis is then used as a statistical measure to discover determinant aspects of overall ratings. The results reveal that cost performance, image quality and product integrity are the three most influential aspects. The practical implication of our research is that merchants can efficiently modify their products, to satisfy more customers and also boost sales performance.     

A hybrid simulation-adaptive network based fuzzy inference system for improvement of electricity consumption estimation

This paper presents a hybrid adaptive network based fuzzy inference system (ANFIS), computer simulation and time series algorithm to estimate and predict electricity consumption estimation. The difficulty with electricity consumption estimation modeling approach such as time series is the reason for proposing the hybrid approach of this study. The algorithm is ideal for uncertain, ambiguous and complex estimation and forecasting. Computer simulation is developed to generate random variables for monthly electricity consumption. Various structures of ANFIS are examined and the preferred model is selected for estimation by the proposed algorithm. Finally, the preferred ANFIS and time series models are selected by Granger–Newbold test. Monthly electricity consumption in Iran from 1995 to 2005 is considered as the case of this study. The superiority of the proposed algorithm is shown by comparing its results with genetic algorithm (GA) and artificial neural network (ANN). This is the first study that uses a hybrid ANFIS computer simulation for improvement of electricity consumption estimation.     

A joint model for analyzing topic and sentiment dynamics from large-scale online news

Many of today’s online news websites and aggregator apps have enabled users to publish their opinions without respect to time and place. Existing works on topic-based sentiment analysis of product reviews cannot be applied to online news directly because of the following two reasons: (1) The dynamic nature of news streams require the topic and sentiment analysis model also to be dynamically updated. (2) The user interactions among news comments can easily lead to inaccurate topic extraction and sentiment classification. In this paper, we propose a novel probabilistic generative model (DTSA) to extract topics and the specified sentiments from news streams and analyze their evolution over time simultaneously. In DTSA, three different timescale models are studied to account for the historical dependencies of sentiment-topic word distributions at current epoch, continuous, skip and multiple timescale models. Additionally, we further consider the links among news comments to avoid the error caused by user interactions. In order to mine more interpretable topics, a Conditional Random Fields (CRF) model is adopted to label a set of meaningful phrases for augmenting the bag-of-word features. Finally, we derive distributed online inference procedures to update the model with newly arrived data and show the effectiveness of our proposed model on real-world data sets.     

基于语义规则与RNN模型的在线评论情感分类研究

为提高互联网中在线评论文本的情感倾向分类准确率,方便消费者和商家准确高效地获取信息,该文提出一种将语义规则方法与深度学习方法相结合的在线评论文本情感分类模型,对基于情感词典的语义规则信息进行扩展,嵌入到常用特征模板中组合成更有效的混合特征模板;采用Fisher判别准则方法对混合特征模板进行降维以消除特征间的信息冗余;深度学习模型采用基于LSTM改进的RNN模型,将网络爬取的数据输入到模型进行训练和测试。结果表明,语义规则抽取出的特征包含更多、更准确的情感信息,使得混合特征模板可以更加全面地考虑文本的情感特征粒度;Fisher准则可有效识别出高判别性的低维文本特征,进一步提高改进RNN模型对评论文本的分类性能。     

EOSentiMiner: an opinion-aware system based on emotion ontology for sentiment analysis of Chinese online reviews

With the growing availability and popularity of online reviews, consumers' opinions towards certain products or services are generated and spread over the Internet; sentiment analysis thus arises in response to the requirement of opinion seekers. Most prior studies are concerned with statistics-based methods for sentiment classification. These methods, however, suffer from weak comprehension of text-based messages at semantic level, thus resulting in low accuracy. We propose an ontology-based opinion-aware framework – EOSentiMiner – to conduct sentiment analysis for Chinese online reviews from a semantic perspective. The emotion space model is employed to express emotions of reviews in the EOSentiMiner, where sentiment words are classified into two types: emotional words and evaluation words. Furthermore, the former contains eight emotional classes, and the latter is divided into two opinion evaluation classes. An emotion ontology model is then built based on HowNet to express emotion in a fuzzy way. Based on emotion ontology, we evaluate some factors possibly affecting sentiment classification including features of products (services), emotion polarity and intensity, degree words, negative words, rhetoric and punctuation. Finally, sentiment calculation based on emotion ontology is proposed from sentence level to document level. We conduct experiments by using the data from online reviews of cellphone and wedding photography. The result shows the EOSentiMiner outperforms baseline methods in term of accuracy. We also find that emotion expression forms and connection relationship vary across different domains of review corpora.     

Inferring preference correlations from social networks

Identifying consumer preferences is a key challenge in customizing electronic commerce sites to individual users. The increasing availability of online social networks provides one approach to this problem: people linked in these networks often share preferences, allowing inference of interest in products based on knowledge of a consumer’s network neighbors and their interests. This paper evaluates the benefits of inference from online social networks in two contexts: a random graph model and a web site allowing people to both express preferences and form distinct social and preference links. We determine conditions on network topology and preference correlations leading to extended clusters of people with similar interests. Knowledge of when such clusters occur improves the usefulness of social network-based inference for identifying products likely to interest consumers based on information from a few people in the network. Such estimates could help sellers design customized bundles of products and improve combinatorial auctions for complementary products.     

基于情感词抽取与LDA特征表示的情感分析方法

情感分析作为文本挖掘的一个新型领域,可用于分类、归纳用户发布的产品评论,从而有助于商家改善服务,提高产品质量;同时为其他消费者提供购买决策。本文提出一种基于情感词抽取与LDA特征表示的情感分析方法,对产品评论进行褒贬二元分类。在情感词抽取中,采用人工构造的情感词典对预处理之后的文本抽取情感词;用LDA模型建立文档的主题分布,以评论-主题分布作为特征,用SVM分类器进行分类。实验结果表明,本文方法在评论褒贬分类方面有着良好的效果。     

中文网络评论的产品特征提取及情感倾向判定

随着互联网和电子商务的发展,用户在购买或使用商品之后会在网络站点上发表对产品的评论,大量的产品评论中所包含的丰富信息,可以为生产厂商和用户提供重要的决策依据。基于文本的语义和语言分析,提出了从产品评论中提取用户关注的产品特征的方法,并根据用户的关注程度对产品特征进行排序;同时,根据观点词的极性值判定用户对产品特征的情感倾向以及情感倾向强度。本研究采用从互联网上获得的针对笔记本电脑的产品评论作为实验对象,实验结果初步证明该方法具有良好的准确率和召回率。     

NFI: a neuro-fuzzy inference method for transductive reasoning

This paper introduces a novel neural fuzzy inference method-NFI for transductive reasoning systems. NFI develops further some ideas from DENFIS-dynamic neuro-fuzzy inference systems for both online and offline time series prediction tasks. While inductive reasoning is concerned with the development of a model (a function) to approximate data in the whole problem space (induction), and consecutively-using this model to predict output values for a new input vector (deduction), in transductive reasoning systems a local model is developed for every new input vector, based on some closest to this vector data from an existing database (also generated from an existing model). NFI is compared with both inductive connectionist systems (e.g., MLP, DENFIS) and transductive reasoning systems (e.g., K-NN) on three case study prediction/identification problems. The first one is a prediction task on Mackey Glass time series; the second one is a classification on Iris data; and the last one is a real medical decision support problem of estimating the level of renal function of a patient, based on measured clinical parameters for the purpose of their personalised treatment. The case studies have demonstrated better accuracy obtained with the use of the NFI transductive reasoning in comparison with the inductive reasoning systems.     

基于客服对话的产品和服务质量分析

现有的产品和服务质量分析常通过问卷调查或利用商品评论,但存在问卷收集难度大、商品评论中存在无效数据等问题。客服对话作为顾客与商家之间沟通的桥梁,包含了丰富的顾客意见,覆盖了从产品到服务的多个方面,然而现在利用客服对话分析产品和服务质量的研究还较少。提出了一种基于客服对话的产品和服务质量分析方法,首先结合产品特征和服务蓝图,确定产品和服务质量的评价要素,并结合重要性?满意度分析（IPA）法定义评价要素的重要性和满意度指标;然后对客服对话进行主题提取和情感分析,定量分析产品和服务的重要性和满意度。以某消毒除菌产品淘宝旗舰店的真实客服对话为例应用了该方法,建立了18个评价要素,并基于90余万条真实的历史客服对话对评价要素的重要性和满意度进行了量化,从而分析旗舰店产品和服务的质量。最后通过对专业客服的问卷调研,验证了所提方法的有效性。