Application of Sentiment Analysis on Product Review E-Commerce

Basani, Yuniarta; Sibuea, Harris V.; Sianipar, Sinta Ida Patona; Samosir, Jen Presly

doi:10.1088/1742-6596/1175/1/012103

Cited by 22 publications

(10 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the following, we will discuss the performance presented above from both a technical perspective and also the relevance for companies. First, regarding our main results, we have identified contributions from the literature that presented sentiment classification on user reviews (Fang et al, 2015;Nanda et al, 2018;Dey et al, 2016;Colón-Ruiz et al, 2020;Basani et al, 2019;Munna et al, 2020;Pipalia et al, 2020). SVM (e.g.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

How to Use Data to Increase Bike Use by Travelers

Exalto-Sijbrands¹,

Baars²,

Wijers³

et al. 2022

35 Th Bled eConference Digital Restructuring and Human (Re)action

View full text Add to dashboard Cite

The Government of the Netherlands wants to be energy neutral by 2050 (Rijksoverheid, sd). A transition towards nonfossil energy sources also affects transport, which is one of the industries significantly contributing to CO2 emission (Centraal Bureau Statistiek, 2019). Road authorities at municipalities and provinces want a shift from fossil fuel-consuming to zero emission transport choices by their inhabitants. For this the Province of Utrecht has data available. However, they struggle how to deploy data to positively influence inhabitants’ mobility behavior. A problem analysis scoped the research towards data to stimulate cycling. Three interviews, desk research and a survey revealed the gap between the province’s current data-item approach that is infrastructure oriented and the required approach that adopts traveler’s personas to successfully stimulate cycling. For this more precisely defined captured data is needed and the focus should shift from already motivated cyclists to non-cyclers.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Colón-Ruiz et al, 2020), Naive Bayes (e.g. Basani et al, 2019), and Neural Network models (Munna et al, 2020) are some of the most widely used methods in the sentiment classification task, i.e. the same models we have tested in this article.…”

Section: Discussionmentioning

confidence: 99%

How to Use Data to Increase Bike Use by Travelers

Exalto-Sijbrands¹,

Baars²,

Wijers³

et al. 2022

35 Th Bled eConference Digital Restructuring and Human (Re)action

View full text Add to dashboard Cite

show abstract

“…[8,24]), or even the use of capital letters as a way to convey a strong emotion, also addressing the implementation and performance of the algorithms for online recognition. Finally, on an important note, the inclusion of neutral and positive emotions should be considered, extending the representation of the users' cognitive-states for a better understanding and prediction of their consumer behavior, also allowing to compare the generality and relative performance of the proposed methodology with other databases and the different approaches to sentiment recognition found in literature [2,3,15,16,20].…”

Section: Final Remarksmentioning

confidence: 99%

“…In literature, some examples can be found on SA applications for e-commerce comment reviews (such as [2,3,15,16,20]). Besides, it is relevant to point the type of sentiment/affect analysis, in the sense of how are emotions represented.…”

Section: Introductionmentioning

confidence: 99%

“…Related work can be found in literature, dealing with the prediction of positive, neutral and/or negative emotions. On the one hand, applying ensembles of statistical classifiers [15,23], and on the other, with direct applications of statistical classifier models such as Naive Bayes [20] or SVM [2], k-Nearest Neighbors [9], or bi-directional recurrent neural nets [1]. It is important to point out that the performance of the classifiers may differ greatly according to the character of the emotion that is set out to be predicted, mainly showing a higher difficulty for accurately predicting neutral and negative emotions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimating Fuzzy Possibility Functions for E-Commerce Decision Support

Franco

Cadavid

2021

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

An automatic methodology is proposed for extracting valuable information from customer experience and comments after they purchase products, including the prediction of negative opinions from written phrases and the estimation of potential savings from attending unsatisfied customers. The complete methodology consists in natural language pre-processing, the calculation of the Term Frequency -Inverse Document Frequency (TF-IDF) index, the construction of binary classification models for negative opinions, and the estimation of the potential savings from using the knowledge extracted by the predictive models. The function for estimating the savings makes use of soft measures, based on fuzzy possibility functions and the estimation of client churning (given that they are unsatisfied with the delivery). The prediction algorithms for negative emotions are shown to achieve good results when tested with out-of-sample comments coming from social networks, and the complete methodology obtains significant savings when applied for e-commerce customer support.

show abstract