access icon openaccess Recommendation method of smart TV programs reflecting content consumption concentration calculation

This is an open access article published by the IET under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0/)
Received 14/10/2019, Accepted 12/11/2019, Published 13/01/2020

The proliferation of smart TVs and the surge of broadcasting contents due to the effects of Internet broadcasting and the creation of comprehensive programming channels have provided an environment in which various programs can be selected and consumed by TV viewers today. However, it is very time-consuming for users to select the programmes that people want by identifying the contents of a large number of programmes. Therefore, it is necessary to study the recommendation of TV programmes with high user satisfaction based on the user's viewing history. However, the research to date does not consider how focused the programme was when generating a list of programmes viewed by the user. As a result, we recommend TV programmes with relatively low satisfaction by recommending TV programme without distinction between the TV programme and the TV programme. In this study, we propose a method to calculate the concentration of content consumption based on user's TV programme consumption pattern and to recommend smart TV programme based on it. In order to verify the proposed method, we compared the satisfaction with the existing method based on the TV viewing records of the top 100 who had many TV watching records.

Inspec keywords: customer satisfaction; Internet; television broadcasting; multimedia computing; ubiquitous computing; digital television; television; recommender systems; interactive television

Other keywords: smart TV programme; broadcasting contents; TV viewing records; TV programme consumption pattern; TV viewers today; content consumption concentration calculation; smart TV programs; comprehensive programming channels

Subjects: Television and video equipment, systems and applications; Information networks; Multimedia; Computer communications; Radio and television broadcasting

References

    1. 1)
      • 5. Linden, G., Smith, B., York, J.: ‘Amazon.com recommendations: item-to-item collaborative filtering’, IEEE Internet Comput., 2003, 7, (1), pp. 76–80.
    2. 2)
      • 8. Cha, M., Rodriguez, P., Crowcroft, J., et al: ‘Watching television over an IP network’. Proc. of the 8th ACM SIGCOMM Conf. on Internet Measurement, 2008, pp. 71–84.
    3. 3)
      • 6. Pazzani, M.J., Billsus, D.: ‘Content-based recommendation systems’. 2007, (LNCS4321), pp. 325–341.
    4. 4)
      • 10. Tving Air Development Center: Available at http://dev.air.tving.com/api/01/4.
    5. 5)
      • 1. Park, J.-M.: ‘Direction of broadcasting communication policy in the digital fusion period’, J. Korean Inst. Commun. Sci., 2010, 28, (1), pp. 4–8.
    6. 6)
      • 3. Kim, J., Yoon, K.H., Lee, J.-H.: ‘An approach to extract informative rules for web page recommendation by genetic programming’, IEICE Trans. Commun., 2012, E95-B, (5), pp. 1558–1565.
    7. 7)
      • 4. Kim, J., Kim, K., You, K.-H., et al: ‘An approach for music recommendation using content-based analysis and collaborative filtering’, Information, 2012, 15, (5), pp. 1985–1996.
    8. 8)
      • 9. Kim, J., Lee, J.-H.: ‘A novel recommendation approach based on chronological cohesive units in content consuming logs’, Information Sciences, 2019, 470, pp. 141–155.
    9. 9)
      • 2. ChoiceStream: ‘Choicestream 2007 survey of viewer trends in TV and online video’. 2007.
    10. 10)
      • 7. Kim, E., Pyo, S., Park, E., et al: ‘An automatic recommendation scheme of TV program contents for (IP)TV personalization’, IEEE Trans. Broadcast., 2011, 57, (3), pp. 674–684.
http://iet.metastore.ingenta.com/content/journals/10.1049/joe.2019.1199
Loading

Related content

content/journals/10.1049/joe.2019.1199
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading