Table 2 - uploaded by Nicholas Evangelopoulos
Content may be subject to copyright.
Contexts and research topics in citing sources: Study 2, 20-factor solution High-loading article count
Source publication
The body of scholarly works that cite F. W. Taylor’s book The Principles of Scientific Management is examined. Latent Semantic Analysis, a method that statistically estimates the semantic and conceptual content in textual data, is used to analyze 5,057 titles and 671 abstracts of citing sources. Management concepts and practices, research topics an...
Contexts in source publication
Context 1
... of the contextual themes extracted in Study 1 are confirmed by Study 2. However, since the documents in Study 2 have a more complex representation, based on abstracts rather than titles, the 20 factors also account for some more complex concepts. Factor labels and a breakdown of high-loading article counts into three time periods, are presented in Table 2. The percentage of variance explained by each factor is also presented in Table 2. ...
Citations
... Text-based review data analysis is a common method used to analyze key features. Latent Semantic Analysis [16,17] can be utilized to extract hidden semantic patterns of words and phrases that make up the document corpus [18]. ...
With a never-ending stream of reviews propagating online, consumers encounter countless good and bad reviews. Depending on which reviews consumers read, they get a different impression of the product. In this paper, we focused on the relationship between the text and numerical information of reviews to gain a better understanding of the decision-making process of consumers affected by the reviews. We evaluated the decisions that consumers made when encountering the review structure of star ratings paired with comments, with respect to three research questions: (1) how consumers compare two products with reviews, (2) how they individually perceive a product based on the corresponding reviews, and (3) how they interpret star ratings and comments. Through the user study, we confirmed that consumers consider reviews differently according to product presentation conditions. When consumers were comparing products, they were more influenced by star ratings, whereas when they were evaluating individual products, they were more influenced by comments. Additionally, consumers planning to buy a product examined star ratings by more stringent criteria than those who had already purchased the product.
... The specific text mining technique adopted in this study is a well-known technique named Latent Semantic Analysis (Han et al. 2011). Latent semantic analysis is an algebraicstatistical method that can detect the underlying topical structure of a document corpus and extract the hidden semantic structures of words and sentences (Evangelopoulos 2011). Latent Semantic Analysis was first proposed by a group of computer scientists at Bell Communication Research, University of Chicago, and the University of Western in 1988 (Dumais et al. 1988). ...
The landscape of ICOs and its underlying Blockchain technology needs more clarity, given that several overlapping and opposing views exist from governmental institutions, institutional investors, economists, and academia. Those positions stem from confusion, bias, and vested interest. Having consensus from the pioneer entrepreneurs who define Blockchain technology usage, and its marketplace address this need. Furthermore, an agreement on the problems blockchain is solving from the industry perspective would further the understanding of the technology direction and its “raison d’être.” or “reason of existence”. The paper analyzes 4367 businesses that requested funding using ICO whitepapers and raising more than $20 billion US dollars during the most active ICO period. Using Latent Semantic Analyses (LSA), the paper identifies a one-factor solution that explains 98.15% of all ICOs. The paper conducts a second-order analysis that generates an 18-factor solution. Through the empirical analysis, the paper presents its findings as an ICO marketplace stacked layer model. The model is comprised of four layers: (1) Trust; (2) Value exchange; (3) Automation; and (4) Applications to enable value exchange, and an era of new business models. The paper then presents an unbiased, unified entrepreneurial definition of the Blockchain technology usage.
... For example, Hu et al. (2019) constructed STM and extracted topics of hotel consumers' complaints, including "facilities," "service," "location," etc., and aggregated the proportion of keywords under different complaint topics. Additionally, a few studies utilized Latent semantic analysis (LSA; Marcolin et al., 2021;Xu & Li, 2016), which is an algebraic statistical method that detects the underlying topic structure of a document corpus (Evangelopoulos, 2011), to extract factors of satisfaction (dissatisfaction). ...
Due to rising competition and resource constraints, hoteliers need to understand which consumer complaints are more important and severe to prioritize, an issue receiving less attention in existing online review-based complaint studies. This study introduced sentiment analysis to assess the extent of complaints; the complaint topic importance was also considered; by modeling these two indicators, Complaint IPA was constructed to determine complaint severity, and thus assist with prioritization issues. The framework was applied to 99,560 online reviews to demonstrate its effectiveness. Further, we analyzed the complaint characteristics in different market segments, including hotel types and consumer types (business vs. leisure). Results show that business consumers have a higher complaint index; compared to midscale and luxury hotels, economy hotels’ consumers have more severe complaints about the Service and Room. This study extends consumer complaint research by proposing a method of complaint severity assessment and revealing complaint characteristics of different market segments.
... 3.3 Action analysis LSA are information retrieval techniques used to reveal a document corpus's topical structure and to extract underlying the semantic structures of words and sentences (Evangelopoulos, 2011). LSA extract a term corpus matrix that matches the use of words across document sentences, which reduces the text information's dimensionality and uncovers the concepts' underlying semantic structure (Evangelopoulos, 2011). ...
... 3.3 Action analysis LSA are information retrieval techniques used to reveal a document corpus's topical structure and to extract underlying the semantic structures of words and sentences (Evangelopoulos, 2011). LSA extract a term corpus matrix that matches the use of words across document sentences, which reduces the text information's dimensionality and uncovers the concepts' underlying semantic structure (Evangelopoulos, 2011). LSA recently gained attention for uncovering the underlying semantic structure of UGC. ...
... Using this matrix, we applied factor analysis to examine the underlying semantic structure and to further reduce the number of terms from the data matrix to meaningful factors that would be easier to interpret (Xiang et al., 2015;Xu and Li, 2016). In the factor analysis, the rotating term loadings can be applied to interpret the latent semantic factors (Evangelopoulos, 2011). In the current study, we used high-loading terms to interpret associated factors. ...
Purpose
This study aims to explore how marketers can use text mining to analyze actors, actions and performance effects of service encounters by building on the role theory. This enables hotel managers to use introduced methodology to measure and monitor frontline employees’ role behavior and optimize their service.
Design/methodology/approach
The authors’ approach links text mining and importance-performance analysis with role theory’s conceptual foundations taking into account the hotel industry’s specifics to assess the effect of frontline hotel employees’ actions on consumer satisfaction and to derive specific management implications for the hospitality sector.
Findings
This study identifies different actors involved in hotel frontline interactions revealing distinct role behaviors that characterize consumers’ perspectives of service encounters with different role types associated with front-office employees. This research also identifies role performance related to role behavior to improve service encounters.
Practical implications
Customer–employee interactions can be assessed by user-generated contents (UGC). Performance evaluations relate to frontline employee roles associated with distinct role scripts, whereby different hotel segments require tailored role designs. Insights of this study can be used for service optimization, market positioning as well as for improving human resource management practices in the hotel industry.
Originality/value
This study contributes to the service encounter literature by applying role theory in the text mining of UGC to assess frontline employees as actors and the effects of their actions on service quality delivery.
... In this article, Latent Semantic Analysis (LSA) was implemented because it is a well-established text mining method. This method is an algebraic-statistical technique which can extract the hidden semantic patterns of words and phrases form a document corpus by underlying their thematic structure [55,56]. Based on previous studies that used LSA [10,11,57,58], three steps that are included in text mining procedures were implemented. ...
... To assist with factor explanation, we identified each factor with its high-loading terms and documents [11,55]. For each solution, a table including all high-loading terms and documents classified by absolute loadings was developed. ...
Big data analytics provides many opportunities to develop new avenues for understanding hospitality management and to support decision making in this field. User-generated content (UGC) provides benefits for hotel managers to gain feedback from customers and enhance specific product attributes or service characteristics in order to increase business value and support marketing activities. Many scholars have provided significant findings about the determinants of customers’ satisfaction in hospitality. However, most researchers primarily used research methodologies such as customer surveys, interviews, or focus groups to examine the determinants of customers’ satisfaction. Thus, more studies must explore how to use UGC to bridge the gap between guest satisfaction and online reviews. This paper examines and compares the aspects of satisfaction and dissatisfaction of Greek hotels’ guests. Text analytics was implemented to deconstruct hotel guest reviews and then examine their relationship with hotel satisfaction. This paper helps hotel managers determine specific product attributes or service characteristics that impact guest satisfaction and dissatisfaction and how hotel guests’ attitudes to those characteristics are affected by hotels’ market positioning and strategies.
... According to reports, it is estimated that nearly 90% of buyers before doing any purchase they do intend to read online reviews given by other buyers, and it is also estimate around 84% of them trust those online reviews and make their decision based on those positive/negative reviews (Erskine, 2017;Zhao et al., 2015). Based on previous studies, positive reviews show customers' satisfaction towards hotels while negative reviews express dissatisfaction, which could potentially have them both reputationally and financially damaging effect (Xu & Li, 2016). ...
With emergence of digital travel platforms, travellers’ online reviews have become a source of rich information which has a significant role in their perception of the services that influences consumer’s demand for resorts. This study aims to identify and rank influential factors of loyalty and disloyalty of travelers through customer online reviews in traditional resorts using Latent Sentiment Analysis (LSA). Our results indicate factors that creating loyalty and disloyalty toward traditional resorts are different and some of these factors are more significant and different from previous studies in the context of other types of hotels. This study signifies the importance of travellers’ online reviews to the resorts managers and contributes to them to improve loyalty factors and alleviate disloyalty factors.
... In this study, we have used a well-accepted text mining approach: Latent Semantic Analysis (LSA). LSA is an algebraic-statistical method that can detect the underlying topical structure of a document corpus and extract the hidden semantic structures of words and sentences (Evangelopoulos, 2011). Using LSA to examine reviews and conduct summaries is more objective than other approaches due to its mathematical nature. ...
... The text factors covered more that 90% of all the keywords we extracted. The findings of the LSA analysis are similar to factor analysis (Evangelopoulos, 2011). High-loading terms associated with each factor were represented for factor interpretation. ...
Purpose
This study aims at identifying critical success factors of a sustainable mobile banking application using text mining approach.
Design/methodology/approach
A total of 6,073 consumer reviews relating to a mobile banking application were collected and analyzed to meet the study objective. Latent Semantic Analysis (LSA) was done to identify the critical success factors of a sustainable mobile banking application.
Findings
The results indicated that privacy and security, navigation, customer support, convenience and efficiency are the key factors.
Research limitations/implications
The study findings enrich the mobile banking and sustainable service delivery channel literature.
Practical implications
The results are expected to benefit the bankers in delivering effective banking services through a mobile banking application.
Originality/value
Studies in the sustainability are few yet promising particularly the ones that use rigorous statistics suitable on thousands of data points to accomplish the study objectives.
... Additionally, LSA can detect words and phrases that have similar meanings to overcome the ambiguity issues of human language [61]. In LSA, each factor is labeled based on high-loaded terms, and the explanation of LSA results is similar to the explanation of the results for exploratory factor analysis through data analysis [62]. ...
With the rapid development of information technology, platform-facilitated collaborative consumption has recently become attractive to consumers. A comparative study of consumers' online review behavior and its impact on overall satisfaction and demand in the accommodation-sharing economy and the hotel industry indicates that consumers' perceptions and behavior change gradually with changes in the level of sharing—from no sharing when staying in hotel rooms to intensive sharing when sharing rooms through collaborative consumption. Online consumer reviews focus on product and service attributes, and the influential factors of customer satisfaction and demand differ when consumers are at different accommodation-sharing levels. Not all attributes described in online reviews influence overall customer satisfaction. With a higher level of sharing, consumers' valuation changes from more to less tangible attributes. Consumers at a higher sharing level care more about social interaction and economic value than consumers at a lower sharing level. Transaction costs, particularly the information search and acquisition costs, play an important role in influencing customer purchase decisions in the sharing economy. Consumers refer to direct information for tangible attributes and to previous consumers' online reviews for intangible attributes to familiarize themselves with details before making purchase decisions. Our study provides implications that help platforms and hosts better target consumer segments with different sharing levels and more effectively utilize online reviews to generate positive electronic word of mouth to enhance consumer demand and the performance of platform economics.
... Kulkarni, Apte and Evangelopoulos (2014) applied LSA to uncover the main Operations Management research topics from 1980 to 2012. Also, Evangelopoulos (2011) also applied LSA to understand the influence of Taylor's ideas among scholarly work. Although there is not a single way to select the optimal number of latent dimensions, which can be pointed out as a limitation, LSA can address some shortcomings from other text analysis methods, as it does not rely on previously notion, limiting any subjective bias in the analysis (Evangelopoulos, 2011;Kulkarni, Apte & Evangelopoulos, 2014). ...
... Also, Evangelopoulos (2011) also applied LSA to understand the influence of Taylor's ideas among scholarly work. Although there is not a single way to select the optimal number of latent dimensions, which can be pointed out as a limitation, LSA can address some shortcomings from other text analysis methods, as it does not rely on previously notion, limiting any subjective bias in the analysis (Evangelopoulos, 2011;Kulkarni, Apte & Evangelopoulos, 2014). For a detailed discussion about dimensionality reduction, see Wild, Stahl, Stermsek, Neumann and Penya (2005). ...
Purpose
This paper aims to elaborate a set of characteristics that conceptualize and qualify a disruptive business model.
Design/methodology/approach
The literature on disruptive business models will be analyzed using the latent semantic analysis (LSA) technique, complemented by content analysis, to obtain a more precise qualification and conceptualization regarding disruptive business models.
Findings
The results found described concepts already described in the theory. However, such findings, highlighted by the LSA, bring new perspectives to the analysis of the disruptive business models, little discussed in the literature and which reveal important considerations to be made on this subject.
Research limitations/implications
It should be noted, about the technique used, a limitation on the choice of the number of singular values. For this to be a problem in the open literature, the authors tried to work not just with the cost-benefit ratio given the addition of each new dimension in the analysis, as well as a criterion of saturation of the terms presented.
Practical implications
The presentation of this set of characteristics can be used as a validation tool to identify if a business is or is not a disruptive business model by managers.
Originality/value
The originality of this paper is the achievement of a consolidated set of characteristics that conceptualize and qualify the disruptive business models by conducting an in-depth analysis of the literature on disruptive business models through the LSA technique, considering the difficulty of obtaining precise concepts on this subject in the literature.
... In this study, we utilize a text mining approach, LSA, and a text regression method to conduct the online review analysis. LSA is an algebraic-statistical method that can detect the underlying topical structure of a document corpus and extract the hidden semantic structures of words, phrases, and sentences (Evangelopoulos, 2011). Using LSA to examine reviews and conduct summaries is objective because of its mathematical nature. ...
... The singular values (square roots of eigenvalues) indicate the importance of a particular factor. The interpretation of LSA results can be similar to the factor analysis interpretation (Evangelopoulos, 2011). In this study, we associated each factor with its documents and high-loading terms to aid in the interpretation of the factor. ...
Do customer online reviews truly reflect the determinants of customer overall satisfaction with hotels? Using a text mining approach: latent semantic analysis and a text regression approach, this study compared the product and service attributes contributing to customer perception on editor-recommended and -nonrecommended hotels at various star levels. This study found that positive and negative attributes contributing to customer perception differ; even for the same attribute, its importance level for customer perception differs between different types of hotels. This study found an asymmetric effect of the focus of online reviews and determinants of customer satisfaction: not all positive/negative textual factors mined from online customer reviews significantly influence their overall satisfaction, and the emphasis level of a certain attribute in customer reviews differs from the relative importance level of the influence of the attribute on customer overall satisfaction. This shows the different psychological mechanisms of customers writing online reviews and their overall satisfaction generation.
