The structural topic model for online review analysis

2018 ◽  
Vol 11 (1) ◽  
pp. 1-17 ◽  
Author(s):  
Eunhye (Olivia) Park ◽  
Bongsug (Kevin) Chae ◽  
Junehee Kwon

Purpose The purpose of this study was to explore influences of review-related information on topical proportions and the pattern of word appearances in each topic (topical content) using structural topic model (STM). Design/methodology/approach For 173,607 Yelp.com reviews written in 2005-2016, STM-based topic modeling was applied with inclusion of covariates in addition to traditional statistical analyses. Findings Differences in topic prevalence and topical contents were found between certified green and non-certified restaurants. Customers’ recognition in sustainable food topics were changed over time. Research limitations/implications This study demonstrates the application of STM for the systematic analysis of a large amount of text data. Originality/value Limited study in the hospitality literature examined the influence of review-level metadata on topic and term estimation. Through topic modeling, customers’ natural responses toward green practices were identified.

2019 ◽  
Vol 15 (1) ◽  
pp. 83-102 ◽  
Author(s):  
Ahmed Amir Tazibt ◽  
Farida Aoughlis

Purpose During crises such as accidents or disasters, an enormous volume of information is generated on the Web. Both people and decision-makers often need to identify relevant and timely content that can help in understanding what happens and take right decisions, as soon it appears online. However, relevant content can be disseminated in document streams. The available information can also contain redundant content published by different sources. Therefore, the need of automatic construction of summaries that aggregate important, non-redundant and non-outdated pieces of information is becoming critical. Design/methodology/approach The aim of this paper is to present a new temporal summarization approach based on a popular topic model in the information retrieval field, the Latent Dirichlet Allocation. The approach consists of filtering documents over streams, extracting relevant parts of information and then using topic modeling to reveal their underlying aspects to extract the most relevant and novel pieces of information to be added to the summary. Findings The performance evaluation of the proposed temporal summarization approach based on Latent Dirichlet Allocation, performed on the TREC Temporal Summarization 2014 framework, clearly demonstrates its effectiveness to provide short and precise summaries of events. Originality/value Unlike most of the state of the art approaches, the proposed method determines the importance of the pieces of information to be added to the summaries solely relying on their representation in the topic space provided by Latent Dirichlet Allocation, without the use of any external source of evidence.


2017 ◽  
Vol 25 (2) ◽  
pp. 209-226 ◽  
Author(s):  
Alessandro Carretta ◽  
Vincenzo Farina ◽  
Paola Schwizer

Purpose This paper aims to analyzing the main risk culture traits of a sample of Central Banks and Supervisory Authorities in Europe as well as of the European Central Bank (ECB). Design/methodology/approach Risk culture is measured through text data processing of the official discourses made by the head Supervisory Authorities, during the years from 1999 to 2012. Findings Results highlight heterogeneous but converging risk cultures for European Union (EU) supervisors and the presence of a “distance” between these cultures and the risk culture of the ECB. Originality/value The paper points out that cultural differences, especially in presence of credit markets still characterized by poor integration, could create unwanted distortion effects during the initial stages of the Banking Union.


2018 ◽  
Vol 38 (9/10) ◽  
pp. 780-793 ◽  
Author(s):  
Vanessa Ratten ◽  
Kayhan Tajeddini

Purpose The purpose of this paper is to review the literature on women’s entrepreneurship and internationalization in order to build an understanding about future trends. There is increasing interest in the role of women in entrepreneurship yet little research has been conducted about the link to internationalization patterns. Design/methodology/approach The literature is reviewed based on a systematic analysis of the words women, female, gender and internationalization. Findings Three main schools of thought around women’s entrepreneurship and internationalization (philosophy, management and motivations) are then discussed. The analysis of literature and classification into main theories enables the building of new research around women’s entrepreneurship and internationalization. Originality/value There is a pipeline of women intending to become entrepreneurs so this paper helps to understand how women entrepreneurs influence internationalization patterns and how to help support women in their business endeavors.


2019 ◽  
Vol 47 (1) ◽  
pp. 55-75 ◽  
Author(s):  
Roxanne van Giesen ◽  
Jorna Leenheer

PurposeThe purpose of this paper is to investigate the potential of digital displays to enhance consumers’ shopping experience and sustainable consumption by more specifically informing consumers on the origin and sustainability of products.Design/methodology/approachAn experimental field study was conducted in the Supermarket of the Future at the World Expo where sustainability information was displayed on interactive screens. There were three experimental groups: supermarket visitors who were put in a sustainability mind-set, supermarket visitors without a sustainability mind-set activation and non-visitors.FindingsStore visitors extensively used the interactive displays, they intent to behave more sustainable in the future, and act more sustainable outside the food domain. Sustainability information through digital displays thus triggers consumers to think more about environmental concerns. Consumers who were activated to process sustainability information before entering the supermarket, show increased interest in the innovative shopping concept. Strong evidence that the increased interest translates into more sustainable consumer choices in the supermarket itself is lacking.Originality/valueThe authors obtain insight in consumer use of sustainability information presented on interactive displays in a retail environment and how this in turn affects behaviour. The study reveals that consumers can successfully be motivated to become more sustainable through interactive displays.


2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Yoritoshi Hara

Purpose This study aims to examine changes in “network logics” that refer to cognitive views socially accepted by actors about the network. These logics provide organizations with templates on how to act in business networks. This study investigates the causes and processes of network logic changes and the phases in the changes. Design/methodology/approach This study relies on content analysis using text data from newspaper articles on global retailers entering the Japanese retail industry. Three different logics were found to describe the actions of the retailers. Two of the logics are related to institutional and strategic logics including network logics, while the third is associated with institutional works that mean actions to create, maintain and disrupt institutions. Findings With regard to transitions in network logics in the Japanese retail industry, the analysis identified four phases: politicization, reflection, establishment and evaluation. Changes in regulative and normative logics were resulted from institutional works of the global retailers into the Japanese market. The findings also include empirical description about how network changes progress through interactions among business actors. Additionally, compared to the regulative and normative logics, it would be difficult to influence the cultural-cognitive logics. Originality/value Business networks often transform with changes in network logics. This study contributes to the literature on industrial network changes by exploring the interactions between macro-level structural states and micro-level events in network logic transitions.


2019 ◽  
Vol 75 (2) ◽  
pp. 334-348 ◽  
Author(s):  
Magdalena Haman ◽  
Morten Hertzum

PurposeResearchers need to collaborate to address grand challenges such as climate change, poverty and sustainable food production. The purpose of this paper is to investigate how the researchers in a globally distributed research program interact to move their research forward.Design/methodology/approachThe authors interviewed 14 participants in the research program.FindingsIn spite of the spatial distribution of the researchers the output from the research program is predominantly collaborative; as much as 79 percent of the publications are co-authored by researchers from multiple countries. However, the researchers mostly work alone on their contributions to their joint work and spend minimal time interacting. This strategy of minimal interaction is punctuated by islands of intense interaction when they occasionally meet in person. Interaction feels natural, productive and satisfying to them when they are co-located but less so when they are distributed, probably because they experience technology-mediated interaction over a distance as somewhat impoverished. The interviewees mention that the minimal-interaction strategy incurs the risks of cracks in common ground and of misconstruing minimal interaction as lack of commitment. But the strategy is generally well-liked.Research limitations/implicationsThe experience of technology-mediated interaction as impoverished points to an explanation for the finding of less interaction in distributed than co-located research. It should be noted that the study is restricted to one research program.Originality/valueBy questioning widely touted recommendations for ongoing, regular and sustained interaction this study provides a fresh look at scientific collaboration.


2016 ◽  
Vol 28 (3) ◽  
pp. 250-273 ◽  
Author(s):  
Marina Dabic ◽  
Ana Colovic ◽  
Olivier Lamotte ◽  
Mollie Painter-Morland ◽  
Silvana Brozovic

Purpose The purpose of this study is to analyze the literature on industry-specific corporate social responsibility (CSR) practices. Design/methodology/approach Using a multiple-keyword search, the authors identified 302 articles reporting on such practices, published in 99 different academic journals between 1995 and 2014. These articles were analyzed to map the CSR literature, identify which industries have been under greater scrutiny and distinguish trends in the most researched industries. Findings The authors’ findings indicate that the CSR studies are very unevenly distributed and that the issues studied and the methods used vary widely across industries. The authors also map this field of study and propose suggestions on where research on industry-specific CSR should go in the future. Originality/value The first extensive, systematic analysis of the industry-specific CSR literature is provided. The current research adds value to the literature by highlighting the key issues investigated, as well as those that require further inquiry.


Author(s):  
Adriana Beatriz Madeira ◽  
Viviana Giampaoli

Purpose This study aims to understand how the institutional and populational characteristics of a Brazilian city, that is, size, gross domestic product (GDP), life expectancy, education, violence and amount of workers benefiting from PAT (Workers’ Food Program) bias the agglomeration of fast-food companies. Design/methodology/approach The research involved 7,653 units distributed among 270 brands of fast-food chains (9 foreign and 261 Brazilian) operating in 542 Brazilian cities in 2015 and institutional and populational characteristics information about them. It calculated the Herfindahl index and implemented mixed inflated beta models. Findings The study found out that the agglomeration of establishments is mainly associated with the city’s income per capita, education, GDP and with some differences regarding the origin of the company, Brazilian or foreign. Research limitations/implications The limitations of the study are the availability of Brazilian cities' data and information about the fast-food companies, such as governance-related information and general infrastructure. The study was cross-sectional, which does not analyze the business installation speed. Practical implications This work provides data collection and analyzes which factors may contribute to the knowledge of the Brazilian fast-food market. It stands out that foreign companies do not seem to contemplate city violence. The proposed models can serve as an investors’ foundation to start, expand business and predict the number of establishments in a city. Originality/value The study highlights the relation between the cities’ institutional and populational characteristics and the aggregation of fast-food chains in Brazilian cities, using index commonly applied in industrial agglomeration.


2017 ◽  
Vol 35 (4) ◽  
pp. 770-782 ◽  
Author(s):  
Qingqing Zhou ◽  
Chengzhi Zhang

Purpose The development of social media has led to large numbers of internet users now producing massive amounts of user-generated content (UGC). UGC, which shows users’ opinions about events directly, is valuable for monitoring public opinion. Current researches have focused on analysing topic evolutions in UGC. However, few researches pay attention to emotion evolutions of sub-topics about popular events. Important details about users’ opinions might be missed, as users’ emotions are ignored. This paper aims to extract sub-topics about a popular event from UGC and investigate the emotion evolutions of each sub-topic. Design/methodology/approach This paper first collects UGC about a popular event as experimental data and conducts subjectivity classification on the data to get subjective corpus. Second, the subjective corpus is classified into different emotion categories using supervised emotion classification. Meanwhile, a topic model is used to extract sub-topics about the event from the subjective corpora. Finally, the authors use the results of emotion classification and sub-topic extraction to analyze emotion evolutions over time. Findings Experimental results show that specific primary emotions exist in each sub-topic and undergo evolutions differently. Moreover, the authors find that performance of emotion classifier is optimal with term frequency and relevance frequency as the feature-weighting method. Originality/value To the best of the authors’ knowledge, this is the first research to mine emotion evolutions of sub-topics about an event with UGC. It mines users’ opinions about sub-topics of event, which may offer more details that are useful for analysing users’ emotions in preparation for decision-making.


2020 ◽  
Vol 37 (8) ◽  
pp. 13-17
Author(s):  
Adeyinka Tella

Purpose This paper aims to examine the coming of robots to libraries and the readiness of their hosts who are the librarians in welcoming and accommodating them. Design/methodology/approach A conceptual and review analysis of documents was adopted to determine the types of robots used in libraries along with their duties, the librarians’ readiness and the likes. Findings There is the fear that the coming of robots to libraries is to take the librarians job; contrarily the arrival of robots to the library is not to replace the librarians but rather to complement their efforts. Originality/value The paper is the original idea by the authors, and it is to get the librarians with limited skills in libraries prepared for up-skilling if they do not want to be replaced by the robots.


Sign in / Sign up

Export Citation Format

Share Document