Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Strategies and limitations in app usage and human mobility

Strategies and limitations in app usage and human mobility

Marco De Nadai

July 18, 2019
Tweet

More Decks by Marco De Nadai

Other Decks in Research

Transcript

  1. Strategies and limitations in app usage
    and human mobility
    Marco De Nadai, Antonio Lima, Angelo Cardoso, Bruno Lepri and Nuria Oliver

    View full-size slide

  2. 2
    Photo: Liz Hafalia, The Chronicle + NBC News

    View full-size slide

  3. 3
    PEOPLE SPEND AN INCREASINGLY
    AMOUNT OF TIME ON THE PHONE […]
    REACHING 3 HOURS PER DAY
    THERE ARE 2.1M APPS IN THE
    GOOGLE PLAY STORE
    App usage statistics by Statista.com & hubspot.net
    USER ENGAGMENT INCREASED BY 23%

    View full-size slide

  4. 4
    ALWAYS USED
    But I always use the same apps!

    View full-size slide

  5. 5
    ALWAYS USED
    MEH... SOMETIMES
    But I always use the same apps!

    View full-size slide

  6. 6
    ALWAYS USED
    MEH... SOMETIMES
    WAS THIS APP EVEN
    HERE?
    • APP USAGE CHANGES
    • APPS CHANGE
    But I always use the same apps!

    View full-size slide

  7. 7
    Monotony
    vs
    Growth of app usage

    View full-size slide

  8. 8
    •Screen time of 90K people
    •Over 8 months
    •69K different apps
    •12M of people’s hours spent on apps
    Data

    View full-size slide

  9. 9
    Data (pseudo-anonymized)

    View full-size slide

  10. 10
    Data (pseudo-anonymized)

    View full-size slide

  11. 11
    Data (pseudo-anonymized)

    View full-size slide

  12. 12
    Data (pseudo-anonymized)
    •Screen time
    •No network-based approaches
    •Unique dataset of app usage

    View full-size slide

  13. 13
    • "
    ~ ( + '
    ))*),
    -
    • = 1.19 ± 0.01
    Characterizing App usage

    View full-size slide

  14. 14
    • "
    ~ ( + '
    ))*),
    -
    • = 1.19 ± 0.01
    Characterizing App usage
    • "
    ~ ())*
    • = 1.27 ± 0.01

    View full-size slide

  15. 15
    • "
    ~ ( + '
    ))*),
    -
    • = 1.19 ± 0.01
    Characterizing App usage
    • "
    ~ ())*
    • = 1.27 ± 0.01
    • ~ 9
    • γ = 0.41

    View full-size slide

  16. 16
    • "
    ~ ( + '
    ))*),
    -
    • = 1.19 ± 0.01
    Characterizing App usage
    • "
    ~ ())*
    • = 1.27 ± 0.01
    • ~ 9
    • γ = 0.41
    • PEOPLE TIME IS FOCUSED ON FEW APPS
    • PEOPLE KEEP EXPLORING NEW APPS

    View full-size slide

  17. 17
    The familiar apps over time: the App space
    THE APP SPACE (t)

    View full-size slide

  18. 18
    • Apps used at least twice and for at least 10 min per week
    • 20 weeks long sliding windows (1 week)
    • How does the App space evolve over time?
    The familiar apps over time: the App space
    THE APP SPACE (t)
    THE APP SPACE (t-1) THE APP SPACE (t+1)
    1 WEEK 1 WEEK

    View full-size slide

  19. App space over time (adopted and dropped apps)
    <
    < = (<) = 4
    THE APP SPACE (t)

    View full-size slide

  20. App space over time (adopted and dropped apps)
    B
    <
    < = (<) = 4
    B = (B) = 5
    THE APP SPACE (t)

    View full-size slide

  21. App space over time (adopted and dropped apps)
    D
    B
    <
    < = (<) = 4
    B = (B) = 5
    D = (D) = 4
    THE APP SPACE (t)

    View full-size slide

  22. App space over time (adopted and dropped apps)
    <)B
    =
    <)B
    =
    B)D
    =
    B)D =
    D
    B
    <
    < = (<) = 4
    B = (B) = 5
    D = (D) = 4
    THE APP SPACE (t)

    View full-size slide

  23. 23
    • Gain: M
    = M
    − M
    ()
    • 97.5% of people exhibit a conserved capacity ( OP
    QRP
    ≤ 1)
    Adoped and dropped apps

    View full-size slide

  24. What is the conserved capacity?
    On average:
    •Everytime a new app is adopted, an older app is discarded
    THE APP SPACE (t)

    View full-size slide

  25. 25
    •Local shuffle: app usage order of a user
    No time consequence (KS: 0.55 p-value < 0.001).
    •Global: app usage among users
    (KS: 0.98 p-value < 0.001). It’s an individual characteristics.
    Is capacity a time-constraints consequence?
    <
    B
    D
    T
    USER A D
    T
    <
    B
    <
    B
    D
    T
    USER A <
    B
    D
    T
    <
    B
    D
    T
    USER B <
    B
    D
    T

    View full-size slide

  26. 26
    The app strategy
    • EXPLORERS (M ≫ )
    • KEEPERS (M
    ≪ )
    • Explorers adopt 1 new app every 28 weeks
    • Keepers always keep using the same apps
    M = M / M

    View full-size slide

  27. 27
    What about age?

    View full-size slide

  28. 28
    What about age?

    View full-size slide

  29. 29
    What about age?
    16
    What about age?

    View full-size slide

  30. 30
    People are focused on few apps, but keep exploring.
    Individuals exhibit a conserved app capacity
    •Capacity is an individual behaviour
    •Capacity varies with age
    •We can define app explorers and keepers
    •AND MORE!
    So?

    View full-size slide

  31. 32
    Strategies and limitations in app
    usage and human mobility
    https://arxiv.org/abs/1904.09350

    View full-size slide

  32. 33
    Apps, Mobility, Social interactions are conserved
    DUNBAR’S NUMBER OF APPS?

    View full-size slide

  33. ANGELO CARDOSO BRUNO LEPRI
    ANTONIO LIMA
    Thank you!
    @denadai2
    NURIA OLIVER

    View full-size slide

  34. 35
    • Alessandretti, Laura, et al. "Evidence for a conserved quantity in human mobility."
    Nature human behaviour 2.7 (2018): 485.
    • Alessandretti, Laura, Sune Lehmann, and Andrea Baronchelli. "Understanding the
    interplay between social and spatial behaviour." EPJ Data Science 7.1 (2018): 36.
    • Pappalardo, Luca, et al. "Returners and explorers dichotomy in human mobility."
    Nature communications 6 (2015): 8166.
    • Miritello, Giovanna, et al. "Limited communication capacity unveils strategies for
    human interaction." Scientific reports 3 (2013): 1950.
    References

    View full-size slide

  35. 36
    Apps that stay the most
    ~10% of apps are always kept
    ~17.5% are continuosly changed

    View full-size slide

  36. 37
    Strategy vs age

    View full-size slide