Research on Extraction of Useful Tourism Online Reviews Based on Multimodal Feature Fusion

Author(s):  
Meng Li

To effectively identify the influencing factors of the perceived usefulness of multimodal data in online reviews of tourism products, this article explores the optimization method of online tourism products based on user-generated content and conducts feature fusion of multimodal data in online reviews of tourism products from the perspective of data fusion analysis. Therefore, based on the word vector model, this article proposes a method to select the seed word set of emotion dictionary. In this method, emotional words are represented in vector form and the distance between word vectors is calculated to form the selection criteria and classification basis of seed word set, and then the sentiment dictionary of online review is formed by category judgment. This article takes the real online review data of tourism products as the research object, carries out descriptive statistical analysis, uses machine learning and deep learning methods, carries out text vector embedding and image content recognition, integrates image and text feature vector, constructs multimodal online review usefulness classification model, and conducts model test. The experimental results show that, compared with the single-mode reviews containing only text or pictures, the multimodal reviews combined with text and pictures can better predict the usefulness of online reviews, improve the quality of online reviews, give full play to the potential value of user-generated content, provide optimization ideas for product providers, and provide decision support for product consumers.

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Ana Isabel Lopes ◽  
Nathalie Dens ◽  
Patrick De Pelsmacker ◽  
Freya De Keyzer

PurposeThis study aims to assess the relative importance of the argument strength, argument sidedness, writing quality, number of arguments, rated review usefulness, summary review rating and number of reviews in determining the perceived usefulness and credibility of an online review. Additionally, the authors use insights from the elaboration likelihood model (ELM) to explore the effect of consumers' product category involvement on the cues' relative importance.Design/methodology/approachA conjoint analysis (N = 287) is used to study the relative importance of the seven previously mentioned attributes. A balanced orthogonal design generated eight cards that correspond to individual reviews. Respondents scored all eight cards in a random order for perceived usefulness and credibility.FindingsOverall, argument strength is the most important cue, while summary review rating and the number of reviews are the least important for perceived review usefulness and credibility. The number of arguments is more important for people who are more highly involved with the product, while writing quality and rated review usefulness are relatively more important for the low-involvement group.Originality/valueThis study provides a comprehensive test of how consumers perceive online reviews, as it the first to the authors’ knowledge to simultaneously investigate a large set of cues using conjoint analysis. This method allows for the implicit valuation (utility) of the individual cues, revealing the cues' relative importance, in a setting that comes close to a real-life context. Besides, insights of the ELM are used to understand how the relative importance of cues differs depending on the level of review readers' product category involvement.


2020 ◽  
Vol 14 (5) ◽  
pp. 759-778
Author(s):  
Tanikan Pipitwanichakarn ◽  
Nittaya Wongtada

Purpose As technology has increasingly disrupted traditional commerce, there is a need for inclusive growth to ensure that no group – particularly the underprivileged – is left behind. Against this backdrop, this paper aims to shed light on mobile commerce (m-commerce) adoption among street vendors. This study conducts an experiment to investigate the contribution of online reviews and relevant factors in enhancing the perceived usefulness and adoption of m-commerce. Design/methodology/approach This study used a 2 (perceived ease of use: high vs low) × 2 (trust in service provider: high vs low) × 2 (online review: positive vs negative) between-subjects design, resulting in eight experimental groups. The level of the online review was manipulated, and the degrees of perceived ease of use and trust were measured. Findings Perceived usefulness depends on online reviews when users perceive incongruent information (e.g. high ease of use but low trust); that is, users who saw positive reviews more strongly perceived the usefulness of m-commerce. On the contrary, perceived usefulness does not vary based on online reviews if users perceive congruent information (e.g. high ease of use and high trust). Originality/value This research advances the knowledge of m-commerce adoption by exploring the interaction of perceived ease of use, trust and online reviews, a combination that has not been addressed in previous empirical studies.


2021 ◽  
Vol 13 (22) ◽  
pp. 12650
Author(s):  
Woohyuk Kim ◽  
Sung-Bum Kim ◽  
Eunhye Park

Although the tourism industry has increasingly used social media, there has been little empirical research in terms of the attributes of tourist satisfaction and dissatisfaction with user-generated contents. The purpose of this study is to explore the attributes of tourist satisfaction and dissatisfaction through user-generated contents. We collected data from online review platforms. Our data include historical online reviews, names of reviewers, ratings, location, helpful votes, date of visits, and contributions. In terms of results, the study found 30 key topics related to tourist satisfaction and dissatisfaction. Additionally, we found three clusters (i.e., holiday experience, attractions and facilities, and food experience). Lastly, we that suggested rating levels are different based on the type of tourists (i.e., domestic and international). This study provides discussions and implications for tourism research and industry practices.


Author(s):  
Bing Wu

AbstractAlthough some studies have explored massive open online courses (MOOCs) discussion forums and MOOC online reviews separately, studies of both aspects are insufficient. Based on the theory of self-determination, this paper proposes research hypotheses that MOOC learning progress has a direct impact on MOOC online reviews and an indirect influence on MOOC online reviews through social interactions in discussion forums, as well. Coursera the largest MOOC platform, is selected as the empirical research object, and data from learners who participated in the MOOC discussion forum and provided MOOC online reviews from August 2016 to December 2019 are obtained from the most popular course, “Machine Learning”. After processing, data from 4376 learners are obtained. Then, according to research hypotheses, multi regression models are constructed accordingly. The results show that the length of MOOC online review text is affected by the MOOC learning progress, the number of discussion forum posts, the number of follow, the online review sentiment and MOOC rating. This study highlights the main factors that affect MOOC online reviews. As a result, some suggestions are put forward for the construction of MOOC.


2021 ◽  
pp. 109634802110303
Author(s):  
Hengyun Li ◽  
Fang Meng ◽  
Simon Hudson

The research aims to examine how positive review disconfirmation (i.e., a positive deviance between a hotel consumer’s poststay evaluation and the average review rating by prior consumers) affects subsequent consumers’ willingness to post online reviews and their own review ratings. By employing an experimental research method, this study reveals that positive review disconfirmation increases hotel guests’ willingness to post online reviews, and increases their online review ratings through the mechanism of concern for others, demonstrating an act of altruism. In addition, comparatively the positive review disconfirmation effects are stronger when the variance of prior review ratings is smaller. This study enhances the online review social influence literature, and the consumer’s altruistic motivation of posting online reviews.


2019 ◽  
Vol 10 (1) ◽  
pp. 2-14 ◽  
Author(s):  
Bruno Oliveira ◽  
Beatriz Casais

Purpose User-generated content and online reviews are highly relevant in purchase decision in the hospitality sector, including restaurants, but there is a lack of knowledge about the effect of sharing pictures in this context. This study aims to focus on the relevance of user-generated photos in online platforms for restaurants’ selection. Design/methodology/approach A research was conducted with a sample of 319 residents of Porto region, who had at least one meal in a restaurant over the 30 days before the answer of the survey and had searched online to select the restaurant. Findings The results show that while doing online research about restaurants, it is important for potential consumers to find pictures of food and physical evidences of restaurants generated by other users. Findings also show that consumers find user-generated photos especially at websites of reviews, although the importance of restaurant owned platforms, such as official social media pages and websites. Practical implications The research results appeal restaurant managers to understand the importance of user-generated photos in online platforms by promoting photo sharing in their restaurants with appropriate marketing activities for that purpose. Originality/value This paper expands the state-of-the-art about the importance of user-generated content, focusing on the importance of photos from restaurants shared by consumers in online platforms.


Prologia ◽  
2021 ◽  
Vol 5 (1) ◽  
pp. 127
Author(s):  
Julian Andrew ◽  
Rezi Erdiansyah

As the people's shopping habits via online starts to emerge, the e-commerce industry in Indonesia has also developed. In 2018, it was noted that 11.9% of Indonesian people were shopping online. However, in the midst of the vastness of online platforms with millions of items found in online storefronts, consumers need more information as their reference to arousing buying interest. As one of the biggest e-commerce players in Indonesia, Tokopedia provides features that enable sellers and consumers to exchange information regarding the items. In Tokopedia, prospective buyers can see electronic word of mouth messages, online reviews, and other additional information about the items that are known to be very influential in generating buying interest. This study uses a quantitative approach with an explanatory type in which the research seeks to find the effect of electronic word of mouth, online review, and the quality of information on buying interest of Jakarta students in Tokopedia e-commerce. The data collection technique used was purposive sampling by distributing questionnaires to 100 samples via online. Based on this research’s results, it was found that electronic word of mouth, online review, and information quality affect buying interest of students in Jakarta by 46% while the other 54% were influenced by other factors not examined in this study.Seiring dengan munculnya kebiasaan berbelanja masyarakat melalui online, industri e-commerce di Indonesia pun turut berkembang. Pada tahun 2018, tercatat bahwa sebanyak 11,9% orang di Indonesia melakukan kegiatan belanja secara online. Namun, di tengah luasnya platform online dengan jutaan barang yang terdapat di etalase online membuat konsumen membutuhkan informasi yang lebih sebagai bahan referensi dalam menimbulkan minat beli. Tokopedia merupakan pelaku e-commerce terbesar di Indonesia menyediakan fitur-fitur yang memungkinkan penjual dan konsumen untuk menulis dan bertukar informasi seputar barang tersebut. Di dalam Tokopedia, para calon pembeli dapat melihat pesan electronic word of mouth, online review, dan informasi-informasi tambahan lainnya seputar barang-barang yang dijual yang diketahui sangat berpengaruh dalam memunculkan minat beli. Penelitian ini menggunakan pendekatan kuantitatif dengan jenis eksplanatif dimana penelitian berusaha menemukan pengaruh e-WOM, kualitas informasi, dan online review terhadap minat beli mahasiswa Jakarta pada e-commerce Tokopedia. Teknik pengumpulan data yang digunakan adalah purposive sampling dengan menyebarkan kuesioner kepada 100 sampel secara online. Penelitian menemukan bahwa electronic word of mouth, online review, dan kualitas informasi berpengaruh terhadap minat beli pada mahasiswa di Jakarta sebanyak 46%, sedangkan 54% dipengaruhi oleh faktor-faktor lain yang tidak diteliti pada penelitian ini.


Sign in / Sign up

Export Citation Format

Share Document