Personalized mobile application discovery

Yang, Cheng; Wang, Tao; Yin, Gang; Wang, Huaimin; Wu, Ming-Jiuan; Xiao, Manjun

doi:10.1145/2666539.2666574

Cited by 48 publications

(69 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Several studies that utilize user's preference extracted from the installed applications for application recommendation have been made. For example, Yan et al [8] proposed an application recommender system called Appjoy, in which a user's preference is expressed as a set of applications that the user often uses. AppGrooves system 1 presents a user two out of his/her installed applications, and asks him/her which one he/her prefers.…”

Section: Related Workmentioning

confidence: 99%

A Preference Extraction Method Using Installed Applications and Their Descriptions

Mizuno

Jun

Hara

et al. 2014

2014 IEEE 33rd International Symposium on Reliable Distributed Systems Workshops

View full text Add to dashboard Cite

As personalization technologies are widely used, preference extraction is becoming important. In this work, we propose a preference extraction method on the basis of applications that are installed on a user's smart device. In this method, keywords are extracted from descriptions of the installed applications on an application market. Then, each keyword is scored by three scoring criteria: degree of characteristic of the keyword in the description, scarcity and usage time of the application. As a result, the user's preference is expressed in the form of a list of pairs of a word and its importance score. From the experimental result, we confirmed that the installed applications are useful as an information source for user preference extraction. We also examined the effectiveness of each of the scoring criteria. From the result, we found that the criterion that represents scarcity of the application is effective for users installing a large number of applications. On the other hand, the criterion that represents usage time of the application tends to be effective for users using their device for a long time.

show abstract

Section: Related Workmentioning

confidence: 99%

A Preference Extraction Method Using Installed Applications and Their Descriptions

Mizuno

Jun

Hara

et al. 2014

2014 IEEE 33rd International Symposium on Reliable Distributed Systems Workshops

View full text Add to dashboard Cite

show abstract

“…For this purpose, we use a dataset provided by the authors of AppJoy [47]. It consists of traces of hourly application usage from 1320 Android users, and is collected between February-September 2011 as part of a public release on the Android marketplace.…”

Section: Cpu Workload Analysismentioning

confidence: 99%

“…A major burden is the interactive usage when the screen is on [16], where the display energy overhead is attributed to the LCD panel, touchscreen, graphics accelerator, and backlight. The Android OS maintains one foreground app activity at a time [47], making the application currently facing the user and the screen the main sources of energy consumption. When running the audio pipelines on the Snapdragon MDP device, we observe that the power consumption is additive as long as the normalized CPU load (across cores) remains below 80%.…”

Section: Cpu Workload Analysismentioning

confidence: 99%

DSP.Ear

Georgiev

Lane

Rachuri

et al. 2014

Proceedings of the 12th ACM Conference on Embedded Network Sensor Systems

View full text Add to dashboard Cite

The rapidly growing adoption of sensor-enabled smartphones has greatly fueled the proliferation of applications that use phone sensors to monitor user behavior. A central sensor among these is the microphone which enables, for instance, the detection of valence in speech, or the identification of speakers. Deploying multiple of these applications on a mobile device to continuously monitor the audio environment allows for the acquisition of a diverse range of sound-related contextual inferences. However, the cumulative processing burden critically impacts the phone battery.To address this problem, we propose DSP.Ear -an integrated sensing system that takes advantage of the latest lowpower DSP co-processor technology in commodity mobile devices to enable the continuous and simultaneous operation of multiple established algorithms that perform complex audio inferences. The system extracts emotions from voice, estimates the number of people in a room, identifies the speakers, and detects commonly found ambient sounds, while critically incurring little overhead to the device battery. This is achieved through a series of pipeline optimizations that allow the computation to remain largely on the DSP. Through detailed evaluation of our prototype implementation we show that, by exploiting a smartphone's co-processor, DSP.Ear achieves a 3 to 7 times increase in the battery lifetime compared to a solution that uses only the phone's main processor. In addition, DSP.Ear is 2 to 3 times more power efficient than a naïve DSP solution without optimizations. We further analyze a large-scale dataset from 1320 Android users to show that in about 80-90% of the daily usage instances DSP.Ear is able to sustain a full day of operation (even in the presence of other smartphone workloads) with a single battery charge.

show abstract

“…PocketNavigator [32], exemplifying most navigation applications, falls into this category. Appazaar [2], AppAware [15] and Appjoy [42] detect users' app usage and location to recommend apps. Interestingly, the recommendation algorithm used in Appjoy would result in it being categorised in quadrant AE as the location data is not used; however it is collected for possible future analysis.…”

Section: Identifiable Data Expected Collection (Ie)mentioning

confidence: 99%

Categorised ethical guidelines for large scale mobile HCI

McMillan¹,

Morrison

Chalmers

2013

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

The recent rise in large scale trials of mobile software using 'app stores' has moved current researcher practice beyond available ethical guidelines. By surveying this recent and growing body of literature, as well as established professional principles adopted in psychology, we propose a set of ethical guidelines for large scale HCI user trials. These guidelines come in two parts: a set of general principles and a framework into which individual app store-based trials can be assessed and ethical concerns exposed. We categorise existing literature using our scheme, and explain how researchers could use our framework to classify their future user trials to determine ethical responsibility, and the steps required to meet these obligations.

show abstract

Personalized mobile application discovery

Cited by 48 publications

References 12 publications

A Preference Extraction Method Using Installed Applications and Their Descriptions

A Preference Extraction Method Using Installed Applications and Their Descriptions

DSP.Ear

Categorised ethical guidelines for large scale mobile HCI

Contact Info

Product

Resources

About