WITHDRAWN: Women’s e-commerce clothing sentiment analysis by probabilistic model LDA using R-SPARK

Parveen, Nikhat; Santhi, M.; Burra, Lakshmi Ramani; Pellakuri, Vidyullatha; Pellakuri, Haran

doi:10.1016/j.matpr.2020.10.064

Cited by 13 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the increasing availability of automatic computational capacities, topic modeling has been used as an efficient, computer-assisted technique for analyzing textual content [ 35 , 36 , 37 ]. Topic models are especially useful for identifying hidden topics based on the word co-occurrence in the corpus of a document.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Consumer Sentiments and Emotions in New Seafood Product Concept Development: A Co-Creation Approach Using Online Discussion Rooms in Croatia, Italy and Spain

Verza

Camanzi

Rota

et al. 2023

Foods

View full text Add to dashboard Cite

Growing Mediterranean seafood consumption, increasing consumers’ awareness of food safety and quality, and changing food lifestyles are leading to the development of new food products. However, the majority of new food products launched on the market are expected to fail within the first year. One of the most effective ways to enhance new product success is by involving consumers during the first phases of New Product Development (NPD), using the so-called co-creation approach. Based on data collected through online discussion rooms, two new seafood product concepts—sardine fillets and sea burgers—were evaluated by a set of potential consumers in three Mediterranean countries—Italy, Spain, and Croatia. Textual information was analyzed by first using the topic modeling technique. Then, for each main topic identified, sentiment scores were calculated, followed by the identification of the main related emotions that were evoked. Overall, consumers seem to positively evaluate both proposed seafood product concepts, and three recurrent positive emotions (trust, anticipation, joy) were identified in relation to the main topics aroused during the discussions. The results of this study will be useful to guide future researchers and actors in this industry in the next development steps of the targeted seafood products in Mediterranean countries.

show abstract

Section: Methodsmentioning

confidence: 99%

“…To do that, in this paper, LDA (Latent Dirichlet allocation) topic modeling was applied [ 38 ]. The LDA is an algorithm used to detect topics and their distribution by the means of the term frequency [ 37 ]. To apply topic modeling in this research, the MALLET (MAchine Learning for LanguagE Toolkit) Java-based package was used [ 39 ].…”

Section: Methodsmentioning

confidence: 99%

Consumer Sentiments and Emotions in New Seafood Product Concept Development: A Co-Creation Approach Using Online Discussion Rooms in Croatia, Italy and Spain

Verza

Camanzi

Rota

et al. 2023

Foods

View full text Add to dashboard Cite

show abstract

“…Moreover, with worldwide e-commerce popularization the importance of analyzing customers attitude to the brand and to the products they buy increased. The sentiment analysis is the key tool to detect clients' mood, indicate specific problems in products or services and prolong clients' life time value (Parveen et al, 2021).…”

Section: Previous Studies' Overviewmentioning

confidence: 99%

Data Science and Marketing in E-Commerce Amid COVID-19 Pandemic

Fedirko¹,

Zatonatska²,

Wołowiec³

et al. 2021

ERSJ

View full text Add to dashboard Cite

Purpose:The objective of this study involves the determination of data-driven solutions needed to increase the usability of e-commerce systems and its profitability. Design/Methodology/Approach: In the research implementation process, logic generalization and induction to identify and analyze the most beneficial data science tools in e-commerce. deign of the study is to generalize existing approaches of data science usage in e-commerce, to develop practical recommendations to ensure the competitive advantages of e-commerce market participants and to estimate the cost of technical tools needed to launch the data science project in e-commerce. Findings: The results clearly demonstrate that in 2020 businesses that have e-commerce system were financially successful and in next 3 years online sales will increase rapidly. The simple analytics will not cover the demand of online business and it is needed to implement advanced data-driven decisions now. Practical Implications: The present research provides generalized knowledge on how to launch a data science project in e-commerce and how to choose the best programming and visualization app to ensure the profitability of a project. The scientific paper gives an instruction on the marketing contribution analysis, which is the tool of key importance for online marketplaces. Originality/Value: The main research value drawn from the study is to launch the datadriven models in e-commerce company it is needed to observe the real business need and available data, find the best programming and visualization tools. It was defined that the most beneficial data science solutions are demand forecasting, estimation of the marketing contribution, customers clustering, recommendation system and customers' attitude analysis. The main business need for each e-commerce company is to estimate the contribution of all marketing channels and advertisement formats separately. This issue may be easily handled with a regression modelling, which helps to understand a set of factors influencing sales.

show abstract

“…Based on the findings of the LDA model, a comprehensive spoilage assessment protocol was proposed that can be used as an indicator to detect possible spoiling of food under different conditions. [Parveen et al, (2021)] et al used LDA topic modelling to analyze online data for women's apparel to enhance shopping experience and get the nerve of customers. R-Spark is used in the implementation of research work.…”

Section: Related Literaturementioning

confidence: 99%

Sentiment Analysis and Topic Modelling on Twitter for Clean India Mission

Rani¹,

Gill²,

Gulia³

2021

INDJCSE

View full text Add to dashboard Cite

Twitter is an important source of information but it is challenging to analyze this data in order to recover meaningful inference. The present paper uses topic modelling and sentiment analysis to draw useful context from Twitter data set related to 'Clean India Mission'. Latent Dirichlet Allocation is used in the research to identify twenty most trending topics and top seven terms related to each of the twenty topics. Coherence and prevalence values represent model efficiency. Topic clustering is also used in the research to identify how strongly topics are related to each other. Five different clusters are created from the top trending topics reflecting different aspects in the corpus. The average silhouette width is employed to determine the optimal number of clusters. Lexicon based classification using 'nrc' sentiment directory is also used to reflect people's sentiment at ten different sentiment levels for the mission. Twitter data for the research is collected from seven different Hashtags, including the official page of the clean India campaign. The most relevant subject segments are identified after evaluating the trending topics by utilizing topic coherence value.

show abstract

WITHDRAWN: Women’s e-commerce clothing sentiment analysis by probabilistic model LDA using R-SPARK

Cited by 13 publications

References 8 publications

Consumer Sentiments and Emotions in New Seafood Product Concept Development: A Co-Creation Approach Using Online Discussion Rooms in Croatia, Italy and Spain

Consumer Sentiments and Emotions in New Seafood Product Concept Development: A Co-Creation Approach Using Online Discussion Rooms in Croatia, Italy and Spain

Data Science and Marketing in E-Commerce Amid COVID-19 Pandemic

Sentiment Analysis and Topic Modelling on Twitter for Clean India Mission

Contact Info

Product

Resources

About