Skip to main content
SpringerLink
Log in

Read to grow: exploring metadata of books to make intriguing book recommendations for teenage readers

  • Regular Paper
  • Published:
Knowledge and Information Systems Aims and scope Submit manuscript

Abstract

It is clearly established that spending time reading is beneficial for an individual’s development in terms of their social, emotional, and intellectual capabilities. This is especially true for teenagers who are in the growing process and reading can improve their memory, vocabulary, concentration and attention span, creativity and imagination, and writing skills. With the overwhelming volume of (online) books available these days, it becomes a huge challenge to find suitable and appealing books to read. Current book recommender systems, however, do not adequately capitalize teenagers’ specific needs such as readability levels, emotional capabilities, and subject’s comprehension, that are more at the forefront for teenage readers than adults and children. To make appropriate recommendations on books for teenagers, we propose a book recommender system, called TBRec. TBRec recommends books to teenagers based on their personal preferences and needs that are determined by using various book features. These features, which include book genres, topic relevance, emotion traits, readers’ advisory, predicted user rating, and readability level, have significant impact on the teenagers’ preference and satisfaction on a book. These distinguished parts of a book, which are premeditated and essential criteria for book selection, identify the type, subject area, state of consciousness, appeal factors, (un)likeness, and complexity of the book content, respectively. Experimental results reveal that TBRec outperforms Amazon, Barnes and Noble, and LibraryThing, three of the widely used book recommenders, in making book recommendations for teenagers, and the results are statistically significant.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Notes

  1. Appeal terms are different from tags created by common users of social media websites, since the latter can be inaccurate, noisy, or ambiguous.

  2. Previews of books can be extracted from the Book Cave dataset, which consists of more than 20,000 teenager books that are made available by publishers to showcase their books.

  3. A subject heading is a set of keywords used by librarians to categorize and index books according to their themes. An example of a subject heading is “Fantasy—Mythical Creatures—Trolls—Green.”

  4. In Read_Level each vector, \(x_{i}\) and \(x_{j}\), represents the heuristics, i.e., readability level features, of a book in a set of books.

  5. Variance is widely used in statistics, along with standard deviation (which is the square root of the variance), to measure the average dispersion of the scores in a distribution.

  6. A recommendation is considered useful if it is regarded as relevant to the corresponding target book determined by librarians recruited at a local school.

  7. Each recommendation is the snippet of the content of a book (limited to the first 500 characters) provided by the publisher of the book.

  8. Two each from TBRec, Amazon, Barnes and Nobles, and LibraryThing which were the top-2 recommendations made by the four recommender systems on a given target book, respectively. The appraisers had no idea which recommendation was made by which book recommender.

References

  1. Ahmed B, Ghabayen A (2020) Review rating prediction framework using deep learning. J Ambient Intell Hum Comput 13:1–10

    Google Scholar 

  2. Alharthi H, Inkpen D, Szpakowicz S (2017) Unsupervised topic modelling in a book recommender system for new users. In: Proceedings of the SIGIR 2017 eCom workshop, p 8

  3. Alharthi H, Inkpen D, Szpakowicz S (2018) A survey of book recommender systems. J Intell Inf Syst 51(1):139–160

    Article  Google Scholar 

  4. Allington E, Gabriel E (2012) Every child, every day. Educ Leadersh 69(6):10–15

    Google Scholar 

  5. Blei D, Ng A, Jordan M (2003) Latent Dirichlet allocation. J Mach Learn Res 3:993–1022

    MATH  Google Scholar 

  6. Bobadilla J, Ortega F, Hernando A et al (2012) A collaborative filtering approach to mitigate the new user cold start problem. Knowl Based Syst 26:225–238

    Article  Google Scholar 

  7. Book Cave (2020) https://mybookcave.com/

  8. BookCrossing (2021) https://www.bookcrossing.com/

  9. Canada NRC (2020) https://saifmohammad.com/WebPages/AffectInten sity.htm

  10. Coleman M (1975) A computer readability formula designed for machine scoring. Appl Psychol 60(2):283–284

    Article  Google Scholar 

  11. Cormack G, Clarke C, Buettcher S (2009) Reciprocal rank fusion outperforms condorcet and individual rank learning methods. In: Proceedings of the international ACM SIGIR conference on research and development in information retrieval. ACM, New York, pp 758–759

  12. Croft B, Metzler D, Strohman T (2010) Search engines: information retrieval in practice. Addison Wesley, San Francisco

    Google Scholar 

  13. Currie D (1997) Decoding femininity: advertisements and their teenage readers. Gen Soc 11(4):453–477

    Article  Google Scholar 

  14. Dali K (2014) From book appeal to reading appeal: redefining the concept of appeal in readers’ advisory. Libr Q 84(1):22–48

    Article  Google Scholar 

  15. Davison A, Kantor R (1982) On the failure of readability formulas to define readable texts: a case study from adaptations. Read Res Q 17(2):187–209

    Article  Google Scholar 

  16. Eldouma S, Adam S (2005) Relationship between reading and writing in English as a second language in the context of performance, perceptions and strategy use. PhD thesis, Universiti Putra Malaysia

  17. Feldman R (2013) Techniques and applications for sentiment analysis. Commun ACM (CACM) 56(4):82–89

    Article  Google Scholar 

  18. Ferrer E, Shaywitz B, Holahan J et al (2015) Achievement gap in reading is present as early as first grade and persists through adolescence. J Pediatr 167(5):1121–1125

    Article  Google Scholar 

  19. Fry E (1968) A readability formula that saves time. J Read 11(7):513–578

    Google Scholar 

  20. Garan E, DeVoogd G (2008) The benefits of sustained silent reading: scientific research and common sense converge. Read Teach 62:336–344. https://doi.org/10.1598/RT.62.4.6

    Article  Google Scholar 

  21. Gelfand A (2000) Gibbs sampling. Am Stat Assoc 95(452):1300–1304

    Article  MathSciNet  MATH  Google Scholar 

  22. Gelles-Watnick R, Perrin A (2021) Who doesn’t read books in America?. https://www.pewresearch.org/fact-tank/2021/09/21/who-doesnt-read-books-in-america/

  23. Genre literary devices: definition and examples of literary terms. https://literarydevices.net/genre/

  24. Goodreads (2020) https://help.goodreads.com/s/article/How-do-I-get-a-copy-of-my-data-from-Goodreads

  25. Goodreads (2021) https://help.goodreads.com

  26. Gu Q, Zhou J, Ding C (2010) Collaborative filtering: weighted nonnegative matrix factorization incorporating user and item graphs. In: Proceedings of the 2010 SIAM international conference on data mining (SDM), pp 199–210

  27. Guthrie J, Hoa A, Wigfield A et al (2007) Reading motivation and reading comprehension growth in the later elementary years. Contemp Educ Psychol 32(3):282–313

    Article  Google Scholar 

  28. Hadaway N (2009) A narrow bridge to academic reading. Support Engl Lang Learn 66(7):38–41

    Google Scholar 

  29. Hill K (2013) The arts and individual well-being in Canada: connections between cultural activities and health, volunteering, satisfaction with life, and other social indicators in 2010. Hill Strategies Research Incorporated, Canada

    Google Scholar 

  30. Howard V (2011) The importance of pleasure reading in the lives of young teens: self-identification, self-construction and self-awareness. Librariansh Inf Sci 43(1):46–55

    Article  Google Scholar 

  31. Institute of School Renaissance (2000) The ATOS readability formula for books and how it compares to other formulas. Tech. Rep. ED449468, ERIC Document Reproduction Service

  32. Iyengar S, Lepper M (2000) When choice is demotivating: Can one desire too much of a good thing? Personal Soc Psychol 79(6):995

    Article  Google Scholar 

  33. Jones B, Kenward M (2003) Design and analysis of cross-over trials, 2nd edn. Chapman and Hall, London

    Book  MATH  Google Scholar 

  34. Kazmier L (2003) Schaum’s outline of business statistics. McGraw-Hill, New York

    Google Scholar 

  35. Kincaid J, Fishburne R, Rogers R et al (1975) Derivation of new readability formulas (automated readability index, fog count, and flesch reading ease formula) for navy enlisted personnel. Tech. Rep. 8-75, Chief of Naval Technical Training

  36. Kingma D, Welling M (2013) Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114

  37. Koren Y, Bell R (2015) Advances in collaborative filtering. In: Recommender systems handbook, pp 77–118

  38. Kowalczyk P (2021) There are now over 10 million publications in the kindle store. https://ebookfriendly.com/over-10-million-kindle-ebooks-on-amazon/

  39. Lee J (1997) Analyses of multiple evidence combination. In: Proceedings of the international ACM SIGIR conference on research and development in information retrieval. ACM, New York, pp 267–276

  40. Liang Z, Huang S, Huang X et al (2020) Post-click behaviors enhanced recommendation system. In: Proceedings of the IEEE 21st international conference on information reuse and integration for data science (IRI), pp 128–135

  41. Liu Y, Zheng Y (2005) One-against-all multi-class SVM classification using reliability measures. In: Proceedings of international joint conference on neural networks (IJCNN’05). IEEE, pp 849–854

  42. Love K, Hamston J (2004) Committed and reluctant male teenage readers: beyond bedtime stories. J Lit Res 36(3):335–400

    Article  Google Scholar 

  43. Manning C, Raghavan P, Schutze H (2008) Introduction to information retrieval. Cambridge University Press, New York

    Book  MATH  Google Scholar 

  44. Milton A, Green M, Keener A et al (2019) StoryTime: eliciting preferences from children for book recommendations. In: Proceedings of the 13th ACM conference on recommender systems (RecSys). ACM, New York, pp 544–545

  45. Milton A, Batista L, Allen G et al (2020) “Don’t judge a book by its cover": exploring book traits children favor. In: Proceedings of the 14th ACM conference on recommender systems (RecSys). ACM, New York, pp 669–674

  46. Minka T (2013) Expectation propagation for approximate Bayesian inference. arXiv preprint arXiv:1301.2294

  47. Mohammad S (2012) From once upon a time to happily ever after: tracking emotions in mail and books. Decis Supp Syst 53(4):730–741

    Article  Google Scholar 

  48. Mortiboys A (2013) Teaching with emotional intelligence: a step-by-step guide for higher and further education professionals. Routledge, London

    Book  Google Scholar 

  49. Pavonetti L, Brimmer K, Cipielewski J (2002) Accelerated reader: What are the lasting effects on the reading habits of middle school students exposed to accelerated reader in elementary grades? Adolesc Adult Lit 46(4):300–311

    Google Scholar 

  50. Pera M (2009) Improving library searches using word-correlation factors and folksonomies. Master’s thesis, Brigham Young University, Provo, Utah

  51. Pera M (2014) Using online data sources to make recommendations on reading material for K-12 and advanced readers. PhD thesis, BYU

  52. Plutchik R (1997) Circumplex models of personality and emotions. In: The circumplex as a general model of the structure of emotions and personality. American Psychological Association, Washington, D.C., pp 17–45

  53. Porteous I, Newman D, Ihler A et al (2008) Fast collapsed gibbs sampling for latent Dirichlet allocation. In: Proceedings of ACM SIGKDD conference on knowledge discovery and data mining. ACM, New York, pp 569–577

  54. Putri T, Zulkarnain (2020) Proposed model of academic reading material recommendation system. In: Proceedings of the 3rd Asia Pacific conference on research in industrial and systems engineering (APCORISE 2020), pp 105–109

  55. Rapport N, Dawson A (2021) The topic and the book. In: Migrants of identity. Routledge, p 3–17

  56. Reader AKC (2021) https://read.amazon.com/

  57. Reagan A, Mitchell L, Kiley D et al (2016) The emotional arcs of stories are dominated by six basic shapes. EPJ Data Sci 5(1):1–12

    Article  Google Scholar 

  58. Rozakis L (2002) Test taking strategies and study skills for the utterly confused. McGraw Hill, New York

    Google Scholar 

  59. Saricks J (2005) Readers’ advisory service in the public library, 3rd edn. ALA American Library Association Store, Atlanta

    Google Scholar 

  60. Sculley D, Wachman G (2007) Relaxed online SVMs for spam filtering. In: Proceedings of the international ACM SIGIR conference on research and development in information retrieval. ACM, New York, pp 415–422

  61. Shu J, Shen X, Liu H et al (2018) A content-based recommendation algorithm for learning resources. Multimed Syst 24:163–173

    Article  Google Scholar 

  62. Smith D, Stenner A, Horabin I et al (1989) The lexile scale in theory and practice: final report. Tech. Rep. ED307577, ERIC Document Reproduction Service

  63. Spache G (1953) A new readability formula for primary-grade reading materials. Eleme Sch 53(7):410–413

    Article  Google Scholar 

  64. Strommen L, Mates B (2004) Learning to love reading: interviews with older children and teens. Adolesc Adult Lit 48(3):188–200

    Article  Google Scholar 

  65. Suthaharan S (2016) Support vector machine. In: Machine learning models and algorithms for big data classification. Springer, pp 207–235

  66. Tang B, Mazzoni D (2006) Multiclass reduced-set support vector machines. In: Proceedings of the 23rd international conference on machine learning (ICML). ACM, New York, pp 921–928

  67. Taylor J, Hora A, Krueger K (2019) Self-selecting books in a children’s fiction collection arranged by genre. J Librariansh Inf Sci 51(3):852–865

    Article  Google Scholar 

  68. Tveit A, Mangen A (2014) A joker in the class: teenage readers’ attitudes and preferences to reading on different devices. Lib Inf Sci Res 36(3–4):179–184

    Article  Google Scholar 

  69. Wanzek J, Vaughn S, Kim A et al (2006) The effects of reading interventions on social outcomes for elementary students with reading difficulties: a synthesis. Read Writ Q 22(2):121–138

    Article  Google Scholar 

  70. Wikipedia (2021) https://en.wikipedia.org/wiki/Wikipedia:Database_download

  71. WordNet (2021) https://wordnet.princeton.edu

  72. Xin Y, Chen Y, Jin L, et al (2017) TeenRead: an adolescents reading recommendation system towards online bibliotherapy. In: Proceedings of the 2017 IEEE international congress on big data (BigData Congress), pp 431–434

  73. Zhou Y (2020) Design and implementation of book recommendation management system based on improved apriori algorithm. Intell Inf Manag 12:75–87

    Google Scholar 

  74. Zuo L, Xiong S, Qi X et al (2021) Communication-based book recommendation in computational social systems. Complexity 2021:10

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Computer Science Department, Brigham Young University, 3361 TMCB, Provo, UT, 84602, USA

    Yiu-Kai Ng

Authors
  1. Yiu-Kai Ng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yiu-Kai Ng.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This work is based on an earlier work: Proceedings of the 2021 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT’21), a short paper.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ng, YK. Read to grow: exploring metadata of books to make intriguing book recommendations for teenage readers. Knowl Inf Syst 65, 4537–4562 (2023). https://doi.org/10.1007/s10115-023-01907-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10115-023-01907-5

Keywords

Search

Navigation