Comparing automated text classification methods

Hartmann, Jochen; Huppertz, Juliana; Schamp, Christina; Heitmann, Mark

doi:10.1016/j.ijresmar.2018.09.009

Cited by 304 publications

(173 citation statements)

References 33 publications

Supporting

Mentioning

139

Contrasting

Unclassified

Order By: Relevance

“…They are trained on single datasets by using various algorithms. The recent review articles analysing state-of-the-art classification algorithms [23,62,72] report that methods, such as Support Vector Machine (SVM), Naive Bayes (NB), Random Forest (RF), Artificial Neural Network (ANN), Decision Tree (DT), are the most frequently applied to text classification. Therefore, in the experiments, we took into account these algorithms.…”

Section: Appendix B: Experiments Resultsmentioning

confidence: 99%

Recognising innovative companies by using a diversified stacked generalisation method for website classification

Mirończuk

Protasiewicz

2019

Appl Intell

View full text Add to dashboard Cite

In this paper, we propose a classification system which is able to decide whether a company is innovative or not, based only on its public website available on the internet. As innovativeness plays a crucial role in the development of myriad branches of the modern economy, an increasing number of entities are expending effort to be innovative. Thus, a new issue has appeared: how can we recognise them? Not only is grasping the idea of innovativeness challenging for humans, but also impossible for any known machine learning algorithm. Therefore, we propose a new indirect technique: a diversified stacked generalisation method, which is based on a combination of a multi-view approach and a genetic algorithm. The proposed approach achieves better performance than all other classification methods which include: (i) models trained on single datasets; or (ii) a simple voting method on these models. Furthermore, in this study, we check if unaligned feature space improves classification results. The proposed solution has been extensively evaluated on real data collected from companies' websites. The experimental results verify that the proposed method improves the classification quality of websites which might represent innovative companies.

show abstract

Section: Appendix B: Experiments Resultsmentioning

confidence: 99%

Recognising innovative companies by using a diversified stacked generalisation method for website classification

Mirończuk

Protasiewicz

2019

Appl Intell

View full text Add to dashboard Cite

show abstract

“…From the computer science perspective, the LIWC‐approach is based on an algorithm that might not capture the range of information that machine learning programs could be trained to do. It is worth noting that LIWC is a user‐friendly program (Hartmann, Huppertz, Schamp, & Heitmann, 2019; Pollach, 2012), particularly for researchers who want to conduct language analysis but cannot write codes in other programming languages, such as Python, Ruby, and C++.…”

Section: Discussionmentioning

confidence: 99%

Your words reveal your thoughts: A two‐wave study of assessing language dimensions in predicting employee turnover intention

Seih

Lepicovsky

Chang

2020

Int J Selection Assessment

View full text Add to dashboard Cite

Assessing turnover intention with explicit approaches (self‐report scales) contains several measurement limitations, including social desirability, impression management, and self‐defense, potentially resulting in reduced accuracy. To improve the accuracy of assessment, the current research conducted a two‐wave study to examine whether implicit variables provide incremental effect in predicting turnover intention, after controlling for explicit variables. A computerized text analysis program, Linguistic Inquiry and Word Count, was used to identify language dimensions in participants' writing samples, and these exported scores serve as implicit language variables. Results demonstrate that language variables provide significant incremental effect (9% of explained variance) in predicting turnover intention, and this effect lasted at a one‐month follow‐up. The language dimensions signal topics of concern associated with turnover intention.

show abstract

“…This unstructured data can often be accessed directly through an application programming interface (API) from social media platforms, scraped manually from webpages, or internally from firm-owned marketing communications, such as image and video advertisements and corresponding meta-data. Although the multi-terabyte scale data makes human coding unfeasible, interest among marketing researchers in classifying large amounts of unstructured data and linking it to marketing outcomes continues to grow (Hartmann, Huppertz, Schamp, & Heitmann, 2019). Fortunately, automated procedures for gathering unstructured data are becoming more accessible.…”

Section: Gather and Sourcementioning

confidence: 99%

Marketing ecosystem: An outside-in view for sustainable advantage

Zhang

Watson

2020

Industrial Marketing Management

View full text Add to dashboard Cite

In the modern business environment, consumers are increasingly influenced by megatrends involving marketplace, technology, socioeconomics, geopolitics, and natural environment. Simultaneously, the data and insights that can inform consumer attitudes and behaviors often reside outside of firms' direct control. Consciously incorporating these interdependent factors into firms' decision-making is essential for adaptability and sustainable profitability. Building on the "outside-in" perspective, we propose that firm strategies should be informed through the lens of the marketing ecosystem that considers the interrelated and dynamic megatrends. By leveraging advances in data and technology, firms can sense-make the marketplace by extracting insights from massive amounts of diverse consumer data with modern-day analytics. By mapping out the megatrends with marketing analytics, firms can 1) more accurately predict consumers' changing preferences and formulate appropriate strategies to engage with them; and 2) become more market-adaptable and competitive in the present and the future. To deliver sustainably compelling value to customers, firms should adopt an ecosystem mindset and cooperate with various stakeholders. A broad-thinking, agile, and humble firm culture can enable the development of more robust outside-in capabilities. We elaborate on the megatrends in the interconnected world of the marketing ecosystem, and propose emerging research directions in each area.

show abstract

Comparing automated text classification methods

Cited by 304 publications

References 33 publications

Recognising innovative companies by using a diversified stacked generalisation method for website classification

Recognising innovative companies by using a diversified stacked generalisation method for website classification

Your words reveal your thoughts: A two‐wave study of assessing language dimensions in predicting employee turnover intention

Marketing ecosystem: An outside-in view for sustainable advantage

Contact Info

Product

Resources

About