Exploiting contextual information to improve call prediction

Fatima, Mehk; Rextin, Aimal; Hayat, Shamaila; Nasim, Mehwish

doi:10.1371/journal.pone.0223780

Cited by 2 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We think a better way to assist these users is to exploit the recent findings from call prediction [ 26 , 78 , 79 , 81 ]. Several studies have proposed algorithms that predict who a user is going to call [ 78 , 79 ] or message [ 26 ] at a given time given the user’s historical communication data.…”

Section: Discussionmentioning

confidence: 99%

“…Hence, at a given time each contact is given a recency score and a frequency score, and these scores are used to compute the most likely to be contacted contacts. Similarly, studies also indicate that users tend to communicate with their different contacts at different times of the day [ 81 ], for example, a work colleague is more likely to be contacted during work hours, while a family member or friend is more likely to be contacted during the evening hours. We think that temporal peculiarities along with frequency and recency scores can be utilized to design an improved contact-book design for emergent users.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Understanding the usability issues in contact management of illiterate and semi-literate users

2021

Self Cite

View full text Add to dashboard Cite

The effective utilization of a communication channel like calling a person involves two steps. The first step is storing the contact information of another user, and the second step is finding contact information to initiate a voice or text communication. However, the current smartphone interfaces for contact management are mainly textual; which leaves many emergent users at a severe disadvantage in using this most basic functionality to the fullest. Previous studies indicated that less-educated users adopt various coping strategies to store and identify contacts. However, all of these studies investigated the contact management issues of these users from a qualitative angle. Although qualitative or subjective investigations are very useful, they generally need to be augmented by a quantitative investigation for a comprehensive problem understanding. This work presents an exploratory study to identify the usability issues and coping strategies in contact management by emergent users; by using a mixture of qualitative and quantitative approaches. We identified coping strategies of the Pakistani population and the effectiveness of these strategies through a semi-structured qualitative study of 15 participants and a usability study of 9 participants, respectively. We then obtained logged data of 30 emergent and 30 traditional users, including contact-books and dual-channel (call and text messages) logs to infer a more detailed understanding; and to analyse the differences in the composition of contact-books of both user groups. The analysis of the log data confirmed problems that affect the emergent users’ communication behaviour due to the various difficulties they face in storing and searching contacts. Our findings revealed serious usability issues in current communication interfaces over smartphones. The emergent users were found to have smaller contact-books and preferred voice communication due to reading/writing difficulties. They also reported taking help from others for contact saving and text reading. The alternative contact management strategies adopted by our participants include: memorizing whole number or last few digits to recall important contacts; adding special character sequence with contact numbers for better recall; writing a contact from scratch rather than searching it in the phone-book; voice search; and use of recent call logs to redial a contact. The identified coping strategies of emergent users could aid the developers and designers to come up with solutions according to emergent users’ mental models and needs.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Understanding the usability issues in contact management of illiterate and semi-literate users

2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Various variations of call prediction algorithms using call logs have been proposed with varying effectiveness [16,[18][19][20][36][37][38]. One of the more established algorithms is proposed by Stefanis et al [2,17] which uses recency and frequency of communication as contextual information and achieved a prediction accuracy of 80%.…”

Section: Call Predictionmentioning

confidence: 99%

“…The dual-channel logs of 111 users were used to evaluate the proposed predictive model. The evaluation of the proposed algorithm for dual-channel prediction was performed by adopting the evaluation mechanism of the different but related problem of call prediction [36,2,11,17]. These studies suggested that a communication prediction algorithm should predict a list of 5-10 alters rather than a single alter.…”

Section: Evaluation Proceduresmentioning

confidence: 99%

Text and phone calls: user behaviour and dual-channel communication prediction

Hayat

Rextin

Idris³

et al. 2020

Hum. Cent. Comput. Inf. Sci.

Self Cite

View full text Add to dashboard Cite

Smartphones allow users to communicate with their social network [1] mostly through verbal, or written communication [2, 3] throughout the day [4, 5] except during resting periods [6]. The volume of this communication may roughly reflect the level of emotional attachment with various social relations [7, 8]. More specifically, if f 1 , f 2 ,. .. , f n , is the reverse sorted fractions of communication volume with n contacts of a user; then a large fraction of communication takes place with only a handful of initial contacts in this sequence [9-12]. Note that contacts can also be referred to as alters, in the sociological

show abstract

Exploiting contextual information to improve call prediction

Cited by 2 publications

References 28 publications

Understanding the usability issues in contact management of illiterate and semi-literate users

Understanding the usability issues in contact management of illiterate and semi-literate users

Text and phone calls: user behaviour and dual-channel communication prediction

Contact Info

Product

Resources

About