Scrutinizing Mobile App Recommendation: Identifying Important App-Related Indicators

@inproceedings{Lin2016ScrutinizingMA,
  title={Scrutinizing Mobile App Recommendation: Identifying Important App-Related Indicators},
  author={Jovian Lin and Kazunari Sugiyama and Min-Yen Kan and Tat-Seng Chua},
  booktitle={AIRS},
  year={2016}
}
Among several traditional and novel mobile app recommender techniques that utilize a diverse set of app-related features (such as an app’s Twitter followers, various version instances, etc.), which app-related features are the most important indicators for app recommendation? In this paper, we develop a hybrid app recommender framework that integrates a variety of app-related features and recommendation techniques, and then identify the most important indicators for the app recommendation task… 

A Framework for APP Discovery Based on Relation Mining

TLDR
This paper proposes a framework of APP discovery for a given user based on APP relation mining, first, Personalized Trust Community (PTC) is constructed based on complex network techniques with “APP-User” data, and fresh APPs based on APPs latent relations are discovered through PTC analysis.

Combining Knowledge Graph Embedding and Network Embedding for Detecting Similar Mobile Applications

TLDR
A novel framework by knowledge graph (KG) techniques and a hybrid embedding strategy to fill above gaps and preliminary results indicate the effectiveness of the method comparing to existing models in terms of reciprocal ranking and minimum ranking.

References

SHOWING 1-10 OF 26 REFERENCES

Serendipitous Recommendation for Mobile Apps Using Item-Item Similarity Graph

TLDR
Experimental results show that the proposed method for recommending serendipitous apps using graph-based techniques can recommend highly novel apps and reduce over-personalization in a recommendation list.

Mobile App Tagging

TLDR
This work proposes a novel auto mobile app tagging framework for annotating a given mobile app automatically, which is based on a search-based annotation paradigm powered by machine learning techniques and demonstrates that the technique is effective and promising.

Addressing cold-start in app recommendation: latent user models constructed from twitter followers

TLDR
This paper describes a method that accounts for nascent information culled from Twitter to provide relevant recommendation in such cold-start situations and significantly outperforms other state-of-the-art recommendation techniques by up to 33%.

Personalized Mobile App Recommendation: Reconciling App Functionality and User Privacy Preference

TLDR
This paper constructs a new model to capture the trade-off between functionality and user privacy preference and finds that it consistently and substantially outperforms the state-of-the-art approaches, which implies the importance ofuser privacy preference on personalized App recommendations.

MOBILE APP RECOMMENDATION

TLDR
There is an opportunity to provide a service that will recommend a relevant application (or set of applications) to users based on information about their current task gathered implicitly from behavioral data and other contextual signals such as user location and time of day.

New and improved: modeling versions to improve app recommendation

TLDR
This work uses a semi-supervised topic model to construct a representation of an app's version as a set of latent topics from version metadata and textual descriptions, and combines state-of-the-art individual and hybrid recommendation techniques to improve recommendation quality.

App recommendation: a contest between satisfaction and temptation

TLDR
This work proposes an Actual- Tempting model that captures factors that invoke a user to replace an old app with a new app and shows that the AT model performs significantly better than the conventional recommendation techniques such as collaborative filtering and content-based recommendation.

Utilizing implicit feedback and context to recommend mobile applications from first use

TLDR
This paper presents a context-aware recommender system for mobile applications which produces recommendations from the first use and presents a prototype implementation of said concepts.

AppJoy: personalized mobile application discovery

TLDR
The AppJoy system that makes personalized application recommendations by analyzing how the user actually uses her installed applications is presented, and the evaluation shows that it consumes little resource on the off-the-shelf Google Android phones.