scholarly journals Can Online Customer Reviews Help Design More Sustainable Products? A Preliminary Study on Amazon Climate Pledge Friendly Products

2021 ◽  
Author(s):  
Michael Saidani ◽  
Harrison Kim ◽  
Nawres Ayadhi ◽  
Bernard Yannou
Keyword(s):  
Language Processing ◽  
Sustainable Design ◽  
Product Category ◽  
Future Research ◽  
Product Reviews ◽  
Learning Tools ◽  
Product Categories ◽  
Sustainable Products ◽  
Online Product Reviews ◽  
Do So

Abstract Online product reviews are a valuable resource for product developers to improve the design of their products. Yet, the potential value of customer feedback to improve the sustainability performance of products is still to be exploited. The present paper investigates and analyzes Amazon product reviews to bring new light on the following question: “What sustainable design insights can be identified or interpreted from online product reviews?”. To do so, the top 100 reviews, evenly distributed by star ratings, for three product categories (laptop, printer, cable) are collected, manually annotated, analyzed and interpreted. For each product category, the reviews of two similar products (one with environmental certification and one standard version) are compared and combined to come up with sustainable design solutions. In all, for the six products considered, between 12% and 20% of the reviews mentioned directly or indirectly aspects or attributes that could be exploited to improve the design of these products from a sustainability perspective. Concrete examples of sustainable design leads that could be elicited from product reviews are given and discussed. As such, this contribution provides a baseline for future work willing to automate this process to gain further insights from online product reviews. Notably, the deployment of machine learning tools and the use of natural language processing techniques to do so are discussed as promising lines for future research.

scholarly journals Mining Health-Related Issues in Consumer Product Reviews by Using Scalable Text Analytics

2016 ◽  
Vol 8s1 ◽  
pp. BII.S37791 ◽  
Author(s):  
Manabu Torii ◽  
Sameer S. Tilak ◽  
Son Doan ◽  
Daniel S. Zisook ◽  
Jung-wei Fan
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Consumer Product ◽  
Future Research ◽  
Product Reviews ◽  
Learning Tools ◽  
Text Analytics ◽  
Related Information ◽  
Online Product Reviews ◽  
Health Related

In an era when most of our life activities are digitized and recorded, opportunities abound to gain insights about population health. Online product reviews present a unique data source that is currently underexplored. Health-related information, although scarce, can be systematically mined in online product reviews. Leveraging natural language processing and machine learning tools, we were able to mine 1.3 million grocery product reviews for health-related information. The objectives of the study were as follows: (1) conduct quantitative and qualitative analysis on the types of health issues found in consumer product reviews; (2) develop a machine learning classifier to detect reviews that contain health-related issues; and (3) gain insights about the task characteristics and challenges for text analytics to guide future research.

scholarly journals Can Machine Learning Tools Support the Identification of Sustainable Design Leads From Product Reviews? Opportunities and Challenges

2021 ◽  
Author(s):  
Michael Saidani ◽  
Harrison Kim ◽  
Bernard Yannou
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Ad Hoc ◽  
Sustainable Design ◽  
Training Model ◽  
Future Research ◽  
Product Reviews ◽  
Sustainable Products ◽  
Review Mining ◽  
Model Training

Abstract The increasing number of product reviews posted online is a gold mine for designers to know better about the products they develop, by capturing the voice of customers, and to improve these products accordingly. In the meantime, product design and development have an essential role in creating a more sustainable future. With the recent advance of artificial intelligence techniques in the field of natural language processing, this research aims to develop an integrated machine learning solution to obtain sustainable design insights from online product reviews automatically. In this paper, the opportunities and challenges offered by existing frameworks — including Python libraries, packages, as well as state-of-the-art algorithms like BERT — are discussed, illustrated, and positioned along an ad hoc machine learning process. This contribution discusses the opportunities to reach and the challenges to address for building a machine learning pipeline, in order to get insights from product reviews to design more sustainable products, including the five following stages, from the identification of sustainability-related reviews to the interpretation of sustainable design leads: data collection, data formatting, model training, model evaluation, and model deployment. Examples of sustainable design insights that can be produced out of product review mining and processing are given. Finally, promising lines for future research in the field are provided, including case studies putting in parallel standard products with their sustainable alternatives, to compare the features valued by customers and to generate in fine relevant sustainable design leads.

Validating Perceived Sustainable Design Features Using a Novel Collage Approach

2021 ◽  
pp. 1-46
Author(s):  
Nasreddine El Dehaibi ◽  
Ting Liao ◽  
Erin F. MacDonald
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Sustainable Design ◽  
Design Method ◽  
Online Reviews ◽  
Design Features ◽  
Sustainable Products ◽  
Low Correlation ◽  
Social Environmental

Abstract Designers are challenged to create sustainable products that resonate with customers, often focusing on engineered sustainability while neglecting perceived sustainability. We previously proposed a method for extracting perceived sustainable features from online reviews using annotations and natural language processing, testing our method with French press coffee carafes. We identified that perceived sustainability may not always align with engineered sustainability. We now investigate how designers can validate perceived features extracted from online reviews using a relatively new design method of collage placement where participants drag and drop products on a collage and select features from a drop-down menu. We created collage activities for participants to evaluate French press products on the three aspects of sustainability: social, environmental, and economic, and on how much they like the products. During the activity participants placed products along the two axes of the collage, sustainability and likeability, and labeled products with descriptive features. We found that participants more often selected our previously extracted features when placing products higher on the sustainability axis, validating that the perceived sustainable features resonate with users. We also measured a low correlation between the two-axes of the collage activity, indicating that perceived sustainability and likeability can be measured separately. In addition, we found that product perceptions across sustainability aspects may differ between demographics. Based on these results, we confirm that the collage is an effective tool for validating sustainability perceptions and that features perceived as sustainable from online reviews resonate with customers when thinking of various sustainability aspects.

Understanding emotionally involved publics

2016 ◽  
Vol 21 (4) ◽  
pp. 465-482 ◽  
Author(s):  
Jeesun Kim ◽  
Yan Jin
Keyword(s):  
Management Practice ◽  
Product Category ◽  
Crisis Response ◽  
Future Research ◽  
Content Type ◽  
Product Categories ◽  
Crisis Type ◽  
Main Effects ◽  
A Company ◽  
Crisis Situations

Purpose The purpose of this paper is to examine the interplay of crisis type and felt involvement as well as product category on publics’ anger toward the company and empathy for the victims. Design/methodology/approach This study uses an experiment based on a 2 (crisis type: accident vs transgression) × 2 (publics’ felt crisis involvement: high vs low) × 2 (product category in crisis: food-related vs technology-related) mixed design. Findings Differential main effects on emotions were detected in different consumer product crises. One of the most interesting findings in this study was the main effects of high felt involvement over low felt involvement in strong feelings of anger toward a company and empathy for the victims in both food- and technology-related crisis situations. There was an interaction effect between crisis type and product category on feelings of anger toward a company. Participants in the food-related crisis condition reported more anger when exposed to a transgression crisis than an accident crisis. Research limitations/implications Future research needs to study other important crisis emotions and to measure them with multiple items instead of a single item. It would be useful to find out what combinations among crisis variables would produce interaction effects to better understand how different publics’ emotions are inducted and processed in different crisis situations. Practical implications The role of felt involvement on public emotions may not be product category specific, but rather be affectively influential across different product categories. From the standpoint of crisis management practice, the main contribution of the present study is to provide empirical evidence that crisis communication managers could use the level of publics’ felt crisis involvement to better predict publics’ emotions that are likely to be felt and displayed in crisis situations. Originality/value This study investigates the crisis-generated discrete emotions as a function of crisis type and felt involvement. Felt involvement should be considered as an important construct due to its potential consequences on publics’ emotions and their behaviors beyond perceptions of crisis responsibility. Crisis response messages should be strategically developed with a consideration of the interplay of crisis type, publics’ felt involvement, and product categories.

Choosing What I Want versus Rejecting What I Do Not Want: An Application of Decision Framing to Product Option Choice Decisions

2000 ◽  
Vol 37 (2) ◽  
pp. 187-202 ◽  
Author(s):  
C. Whan Park ◽  
Sung Youl Jun ◽  
Deborah J. Macinnis
Keyword(s):  
Public Policy ◽  
Option Price ◽  
Product Category ◽  
Future Research ◽  
Decision Framing ◽  
Product Categories ◽  
Price Levels ◽  
Purchase Likelihood ◽  
Anticipate Regret

The authors examine the effects of using a subtractive versus an additive option-framing method on consumers' option choice decisions in three studies. The former option-framing method presents consumers with a fully loaded product and asks them to delete options they do not want. The latter presents them with a base model and asks them to add the options they do want. Combined, the studies support the managerial attractiveness of the subtractive versus the additive option-framing method. Consumers tend to choose more options with a higher total option price when they use subtractive versus additive option framing. This effect holds across different option price levels (Study 1) and product categories of varying price (Study 2). Moreover, this effect is magnified when subjects are asked to anticipate regret from their option choice decisions (Study 2). However, option framing has a different effect on the purchase likelihood of the product category itself, depending on the subject's initial interest in buying within the category. Although subtractive option framing offers strong advantages to managers when product commitment is high, it appears to demotivate category purchase when product commitment is low (Study 3). In addition, the three studies reveal several other findings about the attractiveness of subtractive versus additive option framing from the standpoint of consumers and managers. These findings, in turn, offer interesting public policy and future research implications.

scholarly journals The added value of sustainability motivations in understanding sustainable food choices

2016 ◽  
Vol 10 (2-3) ◽  
pp. 67-76 ◽  
Author(s):  
Muriel C. D. Verain ◽  
Marleen C. Onwezen ◽  
Siet J. Sijtsema ◽  
Hans Dagevos
Keyword(s):  
Social Justice ◽  
Sustainable Consumption ◽  
Product Category ◽  
Addition Product ◽  
Food Choices ◽  
Added Value ◽  
Sustainable Food ◽  
Product Categories ◽  
Sustainable Products ◽  
On Line

Understanding consumer food choices is crucial to stimulate sustainable food consumption. Food choice motives are shown to be relevant in understanding consumer food choices. However, there is a focus on product motives, such as price and taste, whereas process motives (i.e. environmental welfare) are understudied. The current study aims to add to the existing literature by investigating the added value of sustainable process motives (environmental welfare, animal welfare and social justice) above product motives. Two on-line surveys of representative Dutch samples tested whether process motives increase the explained variance of sustainable consumption. The results indicate that sustainable process motives are of added value above product motives in the understanding of consumer food choices. In addition, product categories differ in the sustainable process motives that are most useful in explaining sustainable purchases in that category (Study 1), and different types of sustainable products (organic versus fair trade) differ in the sustainable process motives that are most useful in explaining these purchases (Study 2). In conclusion, this paper shows that understanding of sustainable consumption can be improved by considering sustainable process motives above product motives. Thereby, it is important to take the sustainability dimension (e.g., social justice versus environmental welfare) and the product category (e.g., meat versus fruit) into account.

scholarly journals Online Product Reviews and Their Impact on Third Party Sellers Using Natural Language Processing

2021 ◽  
Vol 12 (1) ◽  
pp. 26-47
Author(s):  
Akash Phaniteja Nellutla ◽  
Manoj Hudnurkar ◽  
Suhas Suresh Ambekar ◽  
Abhay D. Lidbe
Keyword(s):  
Sentiment Analysis ◽  
Language Processing ◽  
Topic Modeling ◽  
Online Reviews ◽  
Third Party ◽  
Bag Of Words ◽  
Product Reviews ◽  
Specific Product ◽  
Online Product Reviews ◽  
The Impact

The purpose of this paper is to gain insights from the online product reviews of e-commerce sites such as Flipkart and Amazon and analyze its impact on third party sellers. To judge the authenticity of a product, reviews are more useful than ratings, since ratings do not give a complete picture. It is always preferred to consider both the product and seller reviews to have a seamless delivery and defect less product. In this paper, natural processing methods are used to gain insights by considering online reviews of a product. Methods such as sentiment analysis, bag of words model help to understand the impact of online product reviews on the seller's ratings and their performance over some time. The reviews are categorized into positive, negative, and neutral using sentiment analysis. Further, topic modeling is done to find out the topic reviews are majorly referring to. The seller reviews for a specific product after analysis are compared with the overall seller reviews to judge the authenticity. The results of this paper would be beneficial to both the consumers and sellers.

scholarly journals Emotion AI-Driven Sentiment Analysis: A Survey, Future Research Directions, and Open Issues

2019 ◽  
Vol 9 (24) ◽  
pp. 5462 ◽  
Author(s):  
Priya Chakriswaran ◽  
Durai Raj Vincent ◽  
Kathiravan Srinivasan ◽  
Vishal Sharma ◽  
Chuan-Yu Chang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Future Research ◽  
Support Vector ◽  
Product Reviews ◽  
Future Research Directions ◽  
Subject Areas ◽  
Short Time ◽  
The Given

The essential use of natural language processing is to analyze the sentiment of the author via the context. This sentiment analysis (SA) is said to determine the exactness of the underlying emotion in the context. It has been used in several subject areas such as stock market prediction, social media data on product reviews, psychology, judiciary, forecasting, disease prediction, agriculture, etc. Many researchers have worked on these areas and have produced significant results. These outcomes are beneficial in their respective fields, as they help to understand the overall summary in a short time. Furthermore, SA helps in understanding actual feedback shared across different platforms such as Amazon, TripAdvisor, etc. The main objective of this thorough survey was to analyze some of the essential studies done so far and to provide an overview of SA models in the area of emotion AI-driven SA. In addition, this paper offers a review of ontology-based SA and lexicon-based SA along with machine learning models that are used to analyze the sentiment of the given context. Furthermore, this work also discusses different neural network-based approaches for analyzing sentiment. Finally, these different approaches were also analyzed with sample data collected from Twitter. Among the four approaches considered in each domain, the aspect-based ontology method produced 83% accuracy among the ontology-based SAs, the term frequency approach produced 85% accuracy in the lexicon-based analysis, and the support vector machine-based approach achieved 90% accuracy among the other machine learning-based approaches.

The effect of product category on consumer brand relationships

2014 ◽  
Vol 23 (2) ◽  
pp. 78-89 ◽  
Author(s):  
Marc Fetscherin ◽  
Michèle Boulanger ◽  
Cid Gonçalves Filho ◽  
Gustavo Quiroga Souki
Keyword(s):  
Purchase Intention ◽  
Soft Drink ◽  
Product Category ◽  
Future Research ◽  
Category Effect ◽  
Brand Relationships ◽  
Content Type ◽  
Product Categories ◽  
Brand Relationship ◽  
Practical Implications

Purpose – This paper aims to investigate the effect of product category on consumer brand relationships. Design/methodology/approach – Based on a total of 800 consumers, respondents evaluated their relationship with their favorite brand in one of the four product categories studied (soft drink, mobile phone, shoes, cars). EFA, subsequent CFA, SEM and ANOVA were used to assess these relationships and the product category effect. Findings – The authors find that brand love positively influences brand loyalty and both, influence positively WOM and purchase intention. Looking at the directionality of these relationships, the results show no product category differences. However, the authors found significant differences in terms of their intensity and their effect on the explanation power of the brand outcome variables WOM and purchase intention. Research limitations/implications – The survey was conducted in Brazil and future research should assess the same product categories in other cultural settings as well as consider other product categories to assess the external validity of these results. Practical implications – This paper demonstrates that consumer brand relationships are not product category specific. However, certain product categories tend to have more intense relationships than other product categories. Originality/value – Despite the importance of the product category effect in the branding literature, this study shows that consumer brand relationship theory can be applied to different product categories. This suggests, the product category is less important in the study design than the unit of analysis which requires to be consumer's favorite brands.

Sign in / Sign up

Export Citation Format

Share Document