Looking for Books in Social Media: An Analysis of Complex Search Requests

Koolen, Marijn; Bogers, Toine; Bosch, Antal van den; Kamps, Jaap

doi:10.1007/978-3-319-16354-3_19

Cited by 26 publications

(31 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Conversely, providing examples of similar books resembles the use of recommender systems. Koolen et al (2015) emphasized that the users often combined several kinds of information in their requests and that such combinations are not supported by current search/recommender systems. The possibility of freely combining different kinds of information in the questions may contribute to explaining the popularity of social Q&A.…”

Section: Social Qandamentioning

confidence: 99%

Music questions in social Q&A: an analysis of Yahoo! Answers

Hertzum

Borlund

2017

View full text Add to dashboard Cite

Purpose -Social question and answer (social Q&A) sites have become a popular tool for obtaining music information. This paper investigates what users ask about, what experience the questions convey, and how users specify their questions.Design/methodology/approach -A total of 3897 music questions from the social Q&A site Yahoo! Answers were categorized according to their question type, user experience, and question specification.Findings -The music questions were diverse with (dis)approval (42%), factual (21%), and advice (15%) questions as the most frequent types. Advice questions were the longest and roughly twice as long as (dis)approval and factual questions. The user experience associated with the questions was most often pragmatic (24%) or senso-emotional (12%). Pragmatic questions were typically about the user's own performance of music, while senso-emotional questions were about finding music for listening. Notably, half of the questions did not convey information about the user experience but the absence of such information did not reduce the number of answers. In specifying the questions, the most frequent information was about the music context and the user context. Research limitations/implications-This study suggests a division of labor between social Q&A sites and search engines for music information retrieval. It should be noted that the study is restricted to one social Q&A site.Originality/value -Social Q&A sites provide an opportunity for studying what information real users seek about music and what information they specify to retrieve it, thereby elucidating the role of social Q&A in music information seeking.

show abstract

Section: Social Qandamentioning

confidence: 99%

Music questions in social Q&A: an analysis of Yahoo! Answers

Hertzum

Borlund

2017

View full text Add to dashboard Cite

show abstract

“…On top of that, in certain contexts of search, content-based recommendation plays a role as well. Personalised IR is strongly related to recommendation, but recent research in book search also identified search scenarios that combine aspects of retrieval and recommendation [8].…”

Section: Motivation and Goalsmentioning

confidence: 99%

Report on RecSys 2014

et al. 2015

Self Cite

View full text Add to dashboard Cite

While content-based recommendation has been applied successfully in many different domains, it has not seen the same level of attention as collaborative filtering techniques have. However, there are many recommendation domains and applications where content and metadata play a key role, either in addition to or instead of ratings and implicit usage data. For some domains, such as movies, the relationship between content and usage data has seen thorough investigation already, but for many other domains, such as books, news, scientific articles, and Web pages we still do not know if and how these data sources should be combined to provided the best recommendation performance. The CBRecSys 2014 workshop aimed to address this by providing a dedicated venue for papers dedicated to all aspects of content-based recommender systems.

show abstract

“…We believe that the design of SWTSs could benefit from a better understanding of real-world search tasks and information needs, and there is rich history of studying this. Recent work by Koolen et al (2015) and Bogers et al (2018 ) has taken a different approach to studying real-world needs by analyzing the complex requests of users in book and movie discovery. Their focus was on the relevance aspects expressed by users in their complex requests, i.e., what makes a book or movie relevant to a person's request?…”

Section: Introductionmentioning

confidence: 99%

Injecting realism into simulated work tasks: A case study of the book domain

Borlund

Bogers

2018

Proc. Assoc. Info. Sci. Tech.

Self Cite

View full text Add to dashboard Cite

Interactive IR studies are commonly conducted by assigning participants simulated work tasks situations (SWTS), predeter‐ mined textual descriptions of an information need and its context to motivate participants to perform realistic searches of the IR system in question. Despite their popularity, research has shown that formulating realistic and engaging SWTSs remains challenging. In this paper, we propose using the analyses of large samples of complex real‐world search requests—with the specific case of book search— to inject realism into SWTSs by taking different relevance aspects and their relative frequencies into account when formulating them. This should make it easier for researchers to design realistic SWTSs in the future.

show abstract

Looking for Books in Social Media: An Analysis of Complex Search Requests

Cited by 26 publications

References 14 publications

Music questions in social Q&A: an analysis of Yahoo! Answers

Music questions in social Q&A: an analysis of Yahoo! Answers

Report on RecSys 2014

Injecting realism into simulated work tasks: A case study of the book domain

Contact Info

Product

Resources

About