Latent Topic Modeling of Consumer Reviews: Linking Text Evaluations to Customer Satisfaction and Brands

2013 ◽  
Author(s):  
Joachim Bueschken ◽  
Greg M. Allenby
Keyword(s):  
Customer Satisfaction ◽  
Topic Modeling ◽  
Consumer Reviews ◽  
Latent Topic

Analysis and Visualization Latent Topic on COVID-19 Vaccine Tweet use two-stage topic modeling (Preprint)

2021 ◽  
Author(s):  
Faizah Faizah ◽  
Bor-Shen Lin
Keyword(s):  
Topic Modeling ◽  
Public Perception ◽  
Latent Dirichlet Allocation ◽  
World Health ◽  
Two Stage ◽  
The Public ◽  
Global Pandemic ◽  
Difficult Time ◽  
Latent Topic ◽  
Latent Topics

BACKGROUND The World Health Organization (WHO) declared COVID-19 as a global pandemic on January 30, 2020. However, the pandemic has not been over yet. Furthermore, in the first quartal of 2021, some countries face the third wave of the pandemic. During the difficult time, the development of the vaccines for COVID-19 accelerates rapidly. Understanding the public perception of the COVID-19 Vaccine according to the data collected from social media can widen the perspective on the state of the global pandemic OBJECTIVE This study explores and analyzes the latent topic on COVID-19 Vaccine Tweet posted by individuals from various countries by using two-stage topic modeling. METHODS A two-stage analysis in topic modeling was proposed to investigating people’s reactions in five countries. The first stage is Latent Dirichlet Allocation that produces the latent topics with the corresponding term distributions that facilitate the investigators to understand the main issues or opinions. The second stage then performs agglomerative clustering on the latent topics based on Hellinger distance, which merges close topics hierarchically into topic clusters to visualize those topics in either tree or graph views. RESULTS In general, the topic discussion regarding the COVID-19 Vaccine in five countries is similar. Topic themes such as "first vaccine" and & "vaccine effect" dominate the public discussion. The remarkable point is that people in some countries have some topic themes, such as "politician opinion" and " stay home" in Canada, "emergency" in India, and & "blood clots" in the United Kingdom. The analysis also shows the most popular COVID-19 Vaccine, which is gaining more public interest. CONCLUSIONS With LDA and Hierarchical clustering, two-stage topic modeling is powerful for visualizing the latent topics and understanding the public perception regarding the COVID-19 Vaccine.

scholarly journals Comment, Rating, Opinion, Review – the Preliminary Research

2021 ◽  
Vol 40 (45) ◽  
pp. 158-169
Author(s):  
Monika Jaworska
Keyword(s):  
Customer Satisfaction ◽  
Social Impact ◽  
Literary Tradition ◽  
The Internet ◽  
Consumer Reviews ◽  
Goods And Services ◽  
Internet Users ◽  
Speech Genres ◽  
Preliminary Research ◽  
Services Use

The article focuses on functional speech genres used on the Internet to assess the level of customer satisfaction after purchasing goods and services on portals with various offers. It attempts to define what genre is used in the texts called commentaries, evaluations, opinions and consumer reviews. Both Internet users and providers of goods and services use these terms interchangeably. The situation may result from the fact that in the ordinary mind, they constitute one genre. The text introduces the research on the statements of internet users expressing their opinion on the transaction, the purchased products, and the service provided. Nowadays, the Internet has such a large social impact that it is important to examine the changes in speech genres existing in the Internet space in relation to their prototypes derived from the literary tradition.

Incorporating Biterm Correlation Knowledge into Topic Modeling for Short Texts

2020 ◽  
Author(s):  
Kai Zhang ◽  
Yuan Zhou ◽  
Zheng Chen ◽  
Yufei Liu ◽  
Zhuo Tang ◽  
...  
Keyword(s):  
Topic Modeling ◽  
Latent Dirichlet Allocation ◽  
Topic Model ◽  
Semantic Knowledge ◽  
Superior Performance ◽  
Knowledge Based ◽  
Modeling Process ◽  
Proposed Model ◽  
Benchmark Datasets ◽  
Latent Topic

Abstract The prevalence of short texts on the Web has made mining the latent topic structures of short texts a critical and fundamental task for many applications. However, due to the lack of word co-occurrence information induced by the content sparsity of short texts, it is challenging for traditional topic models like latent Dirichlet allocation (LDA) to extract coherent topic structures on short texts. Incorporating external semantic knowledge into the topic modeling process is an effective strategy to improve the coherence of inferred topics. In this paper, we develop a novel topic model—called biterm correlation knowledge-based topic model (BCK-TM)—to infer latent topics from short texts. Specifically, the proposed model mines biterm correlation knowledge automatically based on recent progress in word embedding, which can represent semantic information of words in a continuous vector space. To incorporate external knowledge, a knowledge incorporation mechanism is designed over the latent topic layer to regularize the topic assignment of each biterm during the topic sampling process. Experimental results on three public benchmark datasets illustrate the superior performance of the proposed approach over several state-of-the-art baseline models.

scholarly journals Analisis Sentimen Dan Topic Modelling Dalam Aplikasi Ruangguru

2020 ◽  
Vol 4 (1) ◽  
pp. 66
Author(s):  
Muhammad Romy Firdaus ◽  
Fikri Muhammad Rizki ◽  
Favian Muhammad Gaus ◽  
Indra Kusumajati Susanto
Keyword(s):  
Customer Satisfaction ◽  
Sentiment Analysis ◽  
Topic Modeling ◽  
Topic Modelling ◽  
Educational Content ◽  
Learning Space ◽  
Level Of Education ◽  
Important Thing ◽  
Online Tutoring ◽  
Analysis Methods

This study aims to determine and analyze responses regarding customer satisfaction Ruangguru Application to the learning space features in the Ruangguru Application at every level of education. This is useful to know the strengths and weaknesses of the Ruangguru Application based on sentiment responses from Ruangguru users. Ruangguru is an online tutoring startup and a technology-based educational content service and provider no. 1 in Indonesia. So of course, customer satisfaction is an important thing that is the goal of the company. So that when customer satisfaction is met, that is where the company can realize their goals. To see how the level of customer satisfaction, sentiment analysis methods and topic modeling are used in processing the data so that responses can be seen as to what is provided by the customer so that it can be an evaluation for the Ruangguru Application.

What’s yours is mine: exploring customer voice on Airbnb using text-mining approaches

2019 ◽  
Vol 36 (5) ◽  
pp. 655-665 ◽  
Author(s):  
Jurui Zhang
Keyword(s):  
Content Analysis ◽  
Text Mining ◽  
Topic Modeling ◽  
Latent Dirichlet Allocation ◽  
Local Community ◽  
Negative Emotion ◽  
Online Reviews ◽  
Sharing Economy ◽  
Consumer Reviews ◽  
Content Type

Purpose This paper aims to investigate customers’ experiences with Airbnb by text-mining customer reviews posted on the platform and comparing the extracted topics from online reviews between Airbnb and the traditional hotel industry using topic modeling. Design/methodology/approach This research uses text-mining approaches, including content analysis and topic modeling (latent Dirichlet allocation method), to examine 1,026,988 Airbnb guest reviews of 50,933 listings in seven cities in the USA. Findings The content analysis shows that negative reviews are more authentic and credible than positive reviews on Airbnb and that the occurrence of social words is positively related to positive emotion in reviews, but negatively related to negative emotion in reviews. A comparison of reviews on Airbnb and hotel reviews shows unique topics on Airbnb, namely, “late check-in”, “patio and deck view”, “food in kitchen”, “help from host”, “door lock/key”, “sleep/bed condition” and “host response”. Research limitations/implications The topic modeling result suggests that Airbnb guests want to get to know and connect with the local community; thus, help from hosts on ways they can authentically experience the local community would be beneficial. In addition, the results suggest that customers emphasize their interaction with hosts; thus, to improve customer satisfaction, Airbnb hosts should interact with guests and respond to guests’ inquiries quickly. Practical implications Hotel managers should design marketing programs that fulfill customers’ desire for authentic and local experiences. The results also suggest that peer-to-peer accommodation platforms should improve online review systems to facilitate authentic reviews and help guests have a smooth check-in process. Originality/value This study is one of the first to examine consumer reviews in detail in the sharing economy and compare topics from consumer reviews between Airbnb and hotels.

scholarly journals Analysis of launch strategy in cross-border e-Commerce market via topic modeling of consumer reviews

2019 ◽  
Vol 19 (4) ◽  
pp. 863-884 ◽  
Author(s):  
Feifei Wang ◽  
Yang Yang ◽  
Geoffrey K. F. Tso ◽  
Yang Li
Keyword(s):  
Topic Modeling ◽  
Consumer Reviews ◽  
Cross Border ◽  
Launch Strategy
Sign in / Sign up

Export Citation Format

Share Document