Mohammad Aliannejadi

@aliannejadi
50 Followers
42 Following
46 Posts
Ph.D. Candidate at USI, Lugano, Switzerland. Mobile Information Retrieval, Contextual Suggestion.
“A Joint Two-Phase Time-Sensitive Regularized Collaborative Ranking Model for Point of Interest Recommendation” accepted for publication on #IEEE Transactions on Knowledge and Data Engineering #TKDE w/ Dimitrios Rafailidis and Fabio Crestani
@arjenpdevries Hi Arjen.
How strict is the 2+2 page policy of SIGIR demo submissions? I mean, can we not blend the two pages of content with the two pages of figures/tables? Or should we simply put all figure/tables at the end of the paper? I think this would make the layout of the paper a bit unpleasant ;-).

“Understanding Mobile Search Task Relevance and User Behaviour in Context” to appear in #CHIIR2019

• Perpeint: http://bit.ly/2ScBVG8

• Source code of the app used to collect data, called Omicron: http://bit.ly/2S4VZKE

Understanding Mobile Search Task Relevance and User Behaviour in Context

Improvements in mobile technologies have led to a dramatic change in how and when people access and use information, and is having a profound impact on how users address their daily information needs. Smart phones are rapidly becoming our main method of accessing information and are frequently used to perform `on-the-go' search tasks. As research into information retrieval continues to evolve, evaluating search behaviour in context is relatively new. Previous research has studied the effects of context through either self-reported diary studies or quantitative log analysis; however, neither approach is able to accurately capture context of use at the time of searching. In this study, we aim to gain a better understanding of task relevance and search behaviour via a task-based user study (n=31) employing a bespoke Android app. The app allowed us to accurately capture the user's context when completing tasks at different times of the day over the period of a week. Through analysis of the collected data, we gain a better understanding of how using smart phones on the go impacts search behaviour, search performance and task relevance and whether or not the actual context is an important factor.

“Understanding Mobile Search Task Relevance and User Behaviour in Context” to appear in #CHIIR2019

• Perpeint: http://bit.ly/2ScBVG8

• Source code of the app used to collect data, called Omicron: http://bit.ly/2S4VZKE

Understanding Mobile Search Task Relevance and User Behaviour in Context

Improvements in mobile technologies have led to a dramatic change in how and when people access and use information, and is having a profound impact on how users address their daily information needs. Smart phones are rapidly becoming our main method of accessing information and are frequently used to perform `on-the-go' search tasks. As research into information retrieval continues to evolve, evaluating search behaviour in context is relatively new. Previous research has studied the effects of context through either self-reported diary studies or quantitative log analysis; however, neither approach is able to accurately capture context of use at the time of searching. In this study, we aim to gain a better understanding of task relevance and search behaviour via a task-based user study (n=31) employing a bespoke Android app. The app allowed us to accurately capture the user's context when completing tasks at different times of the day over the period of a week. Through analysis of the collected data, we gain a better understanding of how using smart phones on the go impacts search behaviour, search performance and task relevance and whether or not the actual context is an important factor.

"In Situ and Context-Aware Target Apps Selection for Unified Mobile Search" to appear at #CIKM2018; with Zamanii, Crestani, and Croft.

Preprint: bit.ly/2Nzi1Sz

ISTAS data collection: bit.ly/ISTASpage

uSearch Android app code: bit.ly/uSearchOnGitHub

Our paper "In Situ and Context-Aware Target Apps Selection for Unified Mobile Search" with Zamani, Crestani, and Croft accepted as a full paper to #CIKM2018
Our full paper "A Collaborative Ranking Model with Multiple Location-based Similarities for Venue Suggestion" w/ Dimitrios Rafailidis and Fabio Crestani accepted at #ICTIR2018
Our paper on personalized context-aware point of interest recommendation has been accepted at ACM TOIS; pre-print available here: http://bit.ly/2LS7P7n
"Target Apps Selection: Towards a Unified Search Framework for Mobile Devices" to appear at #sigir2018.
Preprint: https://goo.gl/BVmR9Y
Data: https://goo.gl/WCKRzd

#ff #FollowFriday: More Information Retrieval researchers joined the fediverse lately:

@rosswilkinson (structured search,)
@bmitra (neural IR)
@aliannejadi (mobile IR, contextual suggestion)
@Claudia (search as learning,)
@AndrewTrotman (efficiency, ATIRE)
@wesselkraaij (language models, TRECVid)
@TomKenter (word embeddings)
@alansaid (recommender sys)
@fthopf (lifelogging)
@joemon (social media analytics, multimodal interaction)
@[email protected] (IR and knowledge graphs)
@jik (once text genres, Gavagai)