Data on post bank customer reviews from web

Abstract

This document describes a set of customer feedback data concerning the Post Bank. We collected data from 16,659 feedback lines using the Beautiful Soup package from the authoritative site banki.ru is selected as the source of data for collection. The dataset is compiled to monitor the level of trust of bank customers in its banking service. The data presents text reviews for 2013 - 2019 and includes, with or without ratings. Scientists can predict feedback ratings with an empty value in the future. We added additional columns to the dataset with official comments of bank employees, as well as values for the fog-index by Gunning parameter, which is used for the readability of the text. The data can be useful for customer service managers to identify problems in customer service and solve these problems, to assess the dynamics of the appearance of positive and negative reviews of bank customers.

Determining banking service attributes from online reviews: text mining and sentiment analysis

“…, 2015). Despite the popularity of online and mobile banking, the existing literature is not clear to ascertain the extent to which banking service features based on user-generated content affect customer satisfaction (Leem and Eum, 2021; Plotnikov et al. , 2020; Chaturvedi and Chopra, 2014).…”

“…As the role of digital transactions in economic activity has increased, so have banking services globally, including mobile and net banking. Due to the proliferation of mobile and net banking, holistic banking service reviews are now readily available on customer review platforms as a rich source of information to measure customer satisfaction (Plotnikov et al, 2020). Broadly, e-commerce and online review websites collect customer feedback in two ways .…”

“…Most importantly, there is a scarcity of extant literature in banking services that have used online reviews to explain customer satisfaction; if so, hardly any study has combined both quantitative and qualitative aspects to measure it. Few streams of literature assessed the dynamics of positive and negative reviews of banking customers from the web to detect service failures and provide solutions (Leem and Eum, 2021;Plotnikov et al, 2020). Similarly, Chaturvedi and Chopra (2014) manually extracted some banking features from online reviews.…”

“…With the boom in Internet usage and the easy availability of user-generated content on online platforms, the application of text mining has been extensively explored in the e-commerce, food, healthcare, airlines, hotels, travel and tourism industries Chatterjee and Mandal, 2020;Heng et al, 2018;Fang et al, 2016;Engler et al, 2015). Despite the popularity of online and mobile banking, the existing literature is not clear to Determining banking service attributes ascertain the extent to which banking service features based on user-generated content affect customer satisfaction (Leem and Eum, 2021;Plotnikov et al, 2020;Chaturvedi and Chopra, 2014). Notably, the current study identifies core banking service features from online customer reviews and then measures their impact on customer satisfaction.…”

Development the Algorithm for Virtual Screening of Protein Polymorphisms Affecting Their Structural and Functional Properties

“…The algorithm was developed in the form of a script written in the Python v. 3.6.5 (Python Software Foundation, USA) in PyCharm environment (USA). To develop the algorithm, the following plug-in libraries and modules were used: the Requests v.2.24.0 library was used to implement the request; for searching and selecting information from database sites -library Beautifulsoup4 v.4.9.1 (Plotnikov et al, 2020). The script was executed on the command line, and saved to a Microsoft Excel spreadsheet (Microsoft, USA).…”