ALBERT-BPF: a book purchase forecast model for university library by using ALBERT for text feature extraction
| DOI | https://doi.org/10.1108/AJIM-04-2021-0114 |
| Published date | 31 January 2022 |
| Date | 31 January 2022 |
| Pages | 673-687 |
| Subject Matter | Library & information science,Information behaviour & retrieval,Information & knowledge management,Information management & governance,Information management |
| Author | Yejun Wu,Xiaxian Wang,Peilin Yu,YongKai Huang |
ALBERT-BPF: a book purchase
forecast model for university
library by using ALBERT for text
feature extraction
Yejun Wu
Wuhan University Library, Wuhan University, Wuhan, China and
School of Computer Science, Wuhan University, Wuhan, China
Xiaxian Wang
Wuhan University Library, Wuhan University, Wuhan, China
Peilin Yu
School of Computer Science, Wuhan University, Wuhan, China, and
YongKai Huang
Wuhan University Library, Wuhan University, Wuhan, China
Abstract
Purpose –The purpose of this research is to achieve automatic and accurate book purchase forecasts for the
university libraries and improve efficiency of manual book purchase.
Design/methodology/approach –The authors presented a Book Purchase Forecast model with A Lite
BERT(ALBERT-BPF) to achieve their goals. First, the authors process all the book data to unify format of
books’features, such as ISBN, title, authors, brief introduction and so on. Second, they exploit the book order
data to label all books supplied by booksellers with “purchased”or “non-purchased”. The labelled data will be
used for model training. Last, the authors regard the book purchase task as a text classification problem and
present a model named ALBERT-BPF, which applies ALBERT to extract text features of books and BPF
classification layer to forecast purchased books, to solve the problem.
Findings –The application of deep learning in book purchase task is effective. The data the authors exploited
are the historical book purchase data from their university library. The authors’experimentson the data show
that ALBERT-BPF can seek out the books that need to be purchased with an accuracy of over 82%. And the
highest accuracy reached is 88.06%. These indicate that the deep learning model is sufficient to assist the
traditional manual book purchase way.
Originality/value –This research applies ALBERT, which is based on the latest Natural Language
Processing (NLP) architecture Transformer, to library book purchase task.
Keywords Digital libraries, Book purchase, NLP, Text classification, Neural networks, Deep learning
Paper type Research paper
Introduction
As the world has entered the information age, varied information which denotes human
intellectual achievement is constantly converted into electronic resources, including books (Li
and Jiang, 2019). But for libraries, paper books are still an essential component. Therefore,
book purchase is an important task that cannot be avoided for libraries. University libraries
are not exception. As students, we have conducted research on the task of book purchase in
our school library.
At present, most libraries have relatively few big data applications, and they are still in the
era of manual information processing (Anna and Mannan, 2020). Unli ke buying books for
A book
purchase
forecast model
673
This research was supported by Wuhan Science and Technology Planning Application Foundation
Frontier Project (No. 2019010701011413), the National Key Research and Development Program of
China (No. 2018YFC0809804).
The current issue and full text archive of this journal is available on Emerald Insight at:
https://www.emerald.com/insight/2050-3806.htm
Received 6 June 2021
Revised 4 September 2021
20 December 2021
Accepted 25 December 2021
Aslib Journal of Information
Management
Vol. 74 No. 4, 2022
pp. 673-687
© Emerald Publishing Limited
2050-3806
DOI 10.1108/AJIM-04-2021-0114
To continue reading
Request your trial