Gami cation aims at applying game design principles and elements, such as points, badges, feedbacks or leader boards in nongaming environments. An interesting goal of gami cation is to combine and exploit the fun factor for targeting other aspects like achieving more accurate work, more cost e ective solutions and better retention rates. The application of gami cation techniques to IR tasks poses interesting research challenges. In this paper, we propose an analysis of the state of the art in this eld and we summarize interesting challenges and opportunities for the near future.
perceived ease of use of information systems. Successful examples are Foursquare,
Twitter, Stack Over ow, Hacker News. While both Foursquare and Twitter
employ gami cation for increasing their user engagement, Stack Over ow1 and
Hacker News2 are powerful platforms for question answering that promotes also
authoritativeness of trustworthy users with both reward and punishment
mechanisms. Gami cation is thus used for stimulating and promoting users to be
authoritative and active. In gami cation it is important to understand users
and create scenarios that appeal to their personality types: explorers, achievers,
socializers and/or killers. Gami cation can bring various bene ts like increased
engagement, loyalty, time spent, in uence, fun or productivity. A possible
bene t for IR is the understanding that the contribution of user will help raise the
quality of the service and content, thus indirectly the user satisfaction. Bartle
argues that although game design is an art form, gami cation is an application
of psychology, thus one of the most important aspects of gamifying Information
Retrieval (IR) tasks relies on understanding of the human motivation [
An interesting application in IR is relevance assessment. Chamberlain
introduces a model for rewarding and evaluating users using retrospective validation,
with only a small gold standard required to initiate the system [
Web Search
Azzopardi et al. proposed a gami cation-enhanced sequel of Page-Fetch, a
game where participants, given a web page, must enter the query that they
consider most suitable for that page [
Challenges and Opportunities In this paper we discussed the latest research results employing gami cation approaches within IR tasks. We believe that the application of gami cation to IR tasks are still in a preliminary stage. It opens the way to many research challenges, in particular for tasks that are di cult to quantify or qualify, based on crowdsensing, or requiring user evaluation. Here we highlight some promising directions that we believe could be natural scenarios where gami cation can be successfully exploited.
User pro ling: modern Web search engines track the activities of the users in order to derive their pro le to be used and then exploited again during search, for personalizing the search experience. This activity is done by distilling implicit feedback from clicked results, query logs, etc. Gami cation approaches that enable users to select preferences on speci c domains, i.e., documents, images, videos, etc. contribute to building the user pro le explicitly, that in turn allows deriving more precise and detailed information.
Document annotation: modern Web search engines deeply rely on machine learning to perform several important tasks ranging from document and query classi cation to document ranking and spam detection. Machine learning needs labeled data during the training phase. Labeled data is produced by employing hundreds of human assessors judging documents returned by a query and who assign a relevance label. Human labeling is a complex, hard and time-consuming task. For this reason, we believe that by exploiting gami cation, and thus by adding fun and competitiveness to an annotation platform, will lead to more motivated annotators producing higher quality results. The annotation task can be referred to: indicating a certain class of a document (domain, part-of-speech etc.), o ering a relevance judgement (true or false) or ranking objects according to preference, correctness etc.
Diversi cation and Query Intent Discovery: diversi cation of Web search results is an important research eld studying the best way to answer ambiguous or \multi-faceted" search queries. Roughly, diversi cation aims at covering all (the majority of) the possible meanings behind a search query in a single results page. We believe gami cation approaches could help in discovering the most popular interpretations behind a given ambiguous query. The same approach could help in determining the quality of a diversi ed results page.
Gami cation opens the way to many research challenges that has been only partially addressed so far, especially in the IR eld. The proposed literature review also revealed that more rigorous methodologies ought to be used in further research on gami cation.