A machine learning approach to product review disambiguation based on function, form and behavior classification

Singh, Abhinav; Tucker, Conrad S.

doi:10.1016/j.dss.2017.03.007

Cited by 53 publications

(20 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, many researchers examine customer preferences and needs from online product reviews because they describe customer preferences and complaints about a specific product from the users' point of view and thus provide a good channel for informing purchase decisions, customer needs analysis, and product redesign and improvement. For example, Singh and Tucker [28] proposed a machine learning algorithm to predict product function, form, and behavior from online product review data, and they also found that the form of a product was highly correlated with its star rating. In order to mitigate online product rating biases, Lim and Tucker [29] examined reviewers' rating histories and tendencies with an unsupervised model.…”

Section: Related Workmentioning

confidence: 99%

A Machine Learning Approach to Customer Needs Analysis for Product Ecosystems

Zhou

Ayoub

et al. 2019

Journal of Mechanical Design

View full text Add to dashboard Cite

Creating product ecosystems has been one of the strategic ways to enhance user experience and business advantages. Among many, customer needs analysis for product ecosystems is one of the most challenging tasks in creating a successful product ecosystem from both the perspectives of marketing research and product development. In this paper, we propose a machine-learning approach to customer needs analysis for product ecosystems by examining a large amount of online user-generated product reviews within a product ecosystem. First, we filtered out uninformative reviews from the informative reviews using a fastText technique. Then, we extract a variety of topics with regard to customer needs using a topic modeling technique named latent Dirichlet allocation. In addition, we applied a rule-based sentiment analysis method to predict not only the sentiment of the reviews but also their sentiment intensity values. Finally, we categorized customer needs related to different topics extracted using an analytic Kano model based on the dissatisfaction-satisfaction pair from the sentiment analysis. A case example of the Amazon product ecosystem was used to illustrate the potential and feasibility of the proposed method.

show abstract

Section: Related Workmentioning

confidence: 99%

A Machine Learning Approach to Customer Needs Analysis for Product Ecosystems

Zhou

Ayoub

et al. 2019

Journal of Mechanical Design

View full text Add to dashboard Cite

show abstract

“…Singh and Tucker follow up on this work by investigating different machine learning models to classify reviews based on the content of the review using precision, recall, and F-scores to evaluate the model [16]. The authors manually annotated reviews to one of the following categories: function, form, behavior, service, and other content.…”

Section: Extracting Explicit Customer Perceptions Frommentioning

confidence: 99%

Extracting Customer Perceptions of Product Sustainability From Online Reviews

Dehaibi

Goodman

MacDonald

2019

Journal of Mechanical Design

View full text Add to dashboard Cite

In order for a sustainable product to be successful in the market, designers must create products that are not only sustainable in reality but are also sustainable as perceived by the customer—and reality versus perception of sustainability can be quite different. This paper details a design method to identify perceptions of sustainable features (PerSFs) by collecting online reviews, manually annotating them using crowdsourced work, and processing the annotated review fragments with a natural language machine learning algorithm. We analyze all three pillars of sustainability—social, environmental, and economic—for positive and negative perceptions of product features of a French press coffee carafe. For social aspects, the results show that positive PerSFs are associated with intangible features, such as giving the product as a gift, while negative PerSFs are associated with tangible features perceived as unsafe, like sharp corners. For environmental aspects, positive PerSFs are associated with reliable materials like metal while negative PerSFs are associated with the use of plastic. For economic aspects, PerSFs mainly serve as a price constraint for designers to satisfy other customer perceptions. We also show that some crucial sustainability concerns related to environmental aspects, like energy and water consumption, did not have a significant impact on customer sentiment, thus demonstrating the anticipated gap in sustainability perceptions and the realities of sustainable design, as noted in previous literature. From these results, online reviews can enable designers to extract PerSFs for further design study and to create products that resonate with customers' sustainable values.

show abstract

“…Minimizing the words during the text pre-processing phase as much as possible is very important to group similar features and obtain a better prediction. As mentioned in [15], the authors suggest processing the text through stemming and lower casing of words to reduce inflectional forms and derivational affixes from the text. The Porter Stemming algorithm is used to map variations of words (e.g., run, running and runner) into a common root term (e.g., run).…”

Section: B Natural Language Processingmentioning

confidence: 99%

Generating and Analyzing Chatbot Responses using Natural Language Processing

Aleedy¹,

Shaiba²,

Bezbradica³

2019

IJACSA

View full text Add to dashboard Cite

Customer support has become one of the most important communication tools used by companies to provide before and after-sale services to customers. This includes communicating through websites, phones, and social media platforms such as Twitter. The connection becomes much faster and easier with the support of today's technologies. In the field of customer service, companies use virtual agents (Chatbot) to provide customer assistance through desktop interfaces. In this research, the main focus will be on the automatic generation of conversation "Chat" between a computer and a human by developing an interactive artificial intelligent agent through the use of natural language processing and deep learning techniques such as Long Short-Term Memory, Gated Recurrent Units and Convolution Neural Network to predict a suitable and automatic response to customers' queries. Based on the nature of this project, we need to apply sequence-to-sequence learning, which means mapping a sequence of words representing the query to another sequence of words representing the response. Moreover, computational techniques for learning, understanding, and producing human language content are needed. In order to achieve this goal, this paper discusses efforts towards data preparation. Then, explain the model design, generate responses, and apply evaluation metrics such as Bilingual Evaluation Understudy and cosine similarity. The experimental results on the three models are very promising, especially with Long Short-Term Memory and Gated Recurrent Units. They are useful in responses to emotional queries and can provide general, meaningful responses suitable for customer query. LSTM has been chosen to be the final model because it gets the best results in all evaluation metrics.

show abstract

A machine learning approach to product review disambiguation based on function, form and behavior classification

Cited by 53 publications

References 22 publications

A Machine Learning Approach to Customer Needs Analysis for Product Ecosystems

A Machine Learning Approach to Customer Needs Analysis for Product Ecosystems

Extracting Customer Perceptions of Product Sustainability From Online Reviews

Generating and Analyzing Chatbot Responses using Natural Language Processing

Contact Info

Product

Resources

About