A Three-Stage method for Data Text Mining: Using UGC in Business Intelligence Analysis

Abstract

The global development of the Internet, which has enabled the analysis of large amounts of data and the services linked to their use, has led companies to modify their business strategies in search of new ways to increase marketing productivity and profitability. Many strategies are based on business intelligence (BI) and marketing intelligence (MI) that make it possible to extract profitable knowledge and insights from large amounts of data generated by company customers in digital environments. In this context, the present study proposes a three-step research methodology based on data text mining (DTM). In further research, this methodology can be used for business intelligence analysis (BIA) strategies to analyze user generated content (UGC) in social networks and on digital platforms. The proposed methodology unfolds in the following three stages. First, a Latent Dirichlet Allocation (LDA) model that determines the database topic is used. Second, a sentiment analysis (SA) is proposed. This SA is applied to the LDA results to divide the topics identified in the sample into three sentiments. Thirdly, textual analysis (TA) with data text mining techniques is applied on the topics in each sentiment. The proposed methodology offers important advances in data text mining in terms of accuracy, reliability and insight generation for both researchers and practitioners seeking to improve the BIA processes in business and other sectors.

Building Relationships with Customer 4.0 in the Era of Marketing 4.0: The Case Study of Innovative Enterprises in Poland

“…This situation is gaining importance in conditions of dynamic development of Marketing 4.0, which is a kind of technological challenge for enterprises. Clients, as a result of a strong focus on the use of the most modern forms of Internet communication and the use of various ICT technologies, are in a sense a "challenge" for companies that are somewhat "forced" to meet the technological needs of customers (Saura and Bennett 2019). It is also important from the point of view of including Customers 4.0 in the processes of providing services or manufacturing products.…”

Twitter Analyzer—How to Use Semantic Analysis to Retrieve an Atmospheric Image around Political Topics in Twitter

“…According to Saura's Three-Stage Methodological Process of Data Text Mining [14], sentiment analysis constitutes the second stage. In accordance with this approach, this paper focused on this stage and aimed to present a tool that will serve this intermediate stage of all similar analysis approaches.…”

“…All the above-mentioned approaches combine complicated qualitative and quantitative techniques that, in most cases, require the possession of programming skills, artificial intelligence, and machine learning experience [14], along with a deep knowledge of handling and measuring big amounts of data. This combination, although proven impressive in many cases (VADER's creators proved an F1 classification accuracy of 0.96), fails to attract, and sometimes discourages, new researchers in the field of sentiment analysis over short texts produced by social media and consequently microblogging platforms' accounts.…”

“…Future research related to this work could focus on collecting data over a longer time period, for example, over several weeks, and provide a detailed analysis on how accurate the current semantic function is by taking samples from the categorized data out of the database. Overall, the size of the sample area and the semantic area field of any similar application are highlighted as key factors that determine the success of using similar approaches in this field of study [14]. Apart from that, the algorithms used for semantic analysis can be exchanged or improved to increase the accuracy.…”

“…In the present-day digital ecosystem, where more data are generated daily and influence the public opinion, sometimes by fake accounts (bots) [26], new methodological contributions for automatic or semi-automatic effective analysis will be highly appreciated [14].…”