Tutorial: Context-awareness In Information Retrieval and Recommender Systems

163
Tutorial: Context-Awareness In Information Retrieval and Recommender Systems Yong Zheng School of Applied Technology Illinois Institute of Technology, Chicago Time: 2:00 PM – 5:00 PM, Oct 13, 2016 Location: Omaha Hilton, Omaha, NE, USA The 16th IEEE/WIC/ACM Conference on Web Intelligence, Omaha, USA

Transcript of Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Page 1: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Tutorial: Context-Awareness In Information Retrieval and Recommender Systems

Yong ZhengSchool of Applied Technology

Illinois Institute of Technology, Chicago

Time: 2:00 PM – 5:00 PM, Oct 13, 2016Location: Omaha Hilton, Omaha, NE, USA

The 16th IEEE/WIC/ACM Conference on Web Intelligence, Omaha, USA

Page 2: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Introduction

Yong ZhengSchool of Applied TechnologyIllinois Institute of Technology, Chicago, USA2016, PhD in CIS, DePaul University, USADissertation: Context-awareness In Recommender SystemsResearch: Data Science for Web Intelligence

Short Tutorial (2 hrs, non-technical):Schedule: 2:00 PM – 5:00 PM, Oct 13, 2016Break: 3:00 PM – 3:30 PM (Outside Merchants)Location: Herndon, Omaha Hilton, Omaha, USA

2

Page 3: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Topics in this Tutorial

• Information Overload

• Solution: Information Retrieval (IR)e.g., Google Search Engine

• Solution: Recommender Systems (RecSys)

e.g., Movie recommender by Netflix

• Context and Context-awareness

e.g., Mobile computing and smart home devices

• Context-awareness in IR and RecSys

• Extended Topics: Trends, Challenges and Future3

Page 4: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Information Overload

Page 5: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Populations v.s. Flood Information

5

https://www.youtube.com/watch?v=ia5FxoeFJWI

Page 6: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Documents

6

Page 7: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Website

7

Page 8: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Multimedia / Streaming Media

8

Page 9: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Business and Applications

9

Page 10: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Life via Multi-Channel & Multi-Device

10

Page 11: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

We are the victim!

11

Page 12: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Information Overload

12

• Information overload refers to the difficulty a person can have understanding an issue and making decisions that can be caused by the presence of too much information.

• The term is popularized by Alvin Toffler in his bestselling 1970 book “Future Shock”

Page 13: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Information Overload

13

• We are living in the information age

• But, you may want to LEAVE (escape from) the overloaded information age right now.

Page 14: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Alleviating Information Overload

14

Some solutions (Meyer 1998)

• Chunking: Deal with group of things, not individuals

• Omission: Ignore some information

• Queuing: Put information aside & catch up later

• Capitulation: Escape from the task

• Filtering: ignore irrelevant information

• And so forth …Let’s take Emails for example

Page 15: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Alleviating Information Overload

15

Information Extraction and Filtering

Query

Information Retrieval

Recommender Systems

Page 16: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Information Retrieval

Page 17: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Information Retrieval

17

Information Retrieval, one example: Web Search

Page 18: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Information Retrieval

18

Information Retrieval, one example: Web Search

Page 19: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Information Retrieval

19

Information Retrieval, one example: Web Search

Page 20: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Information Retrieval

20

Information Retrieval, one example: Web Search

Page 21: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Information Retrieval

Task In Information Retrieval:

• Given a query

• Retrieve a list of documents related to the query/intent

The query could be a term:

21

Page 22: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Information Retrieval

Task In Information Retrieval:

• Given a query

• Retrieve a list of documents related to the query/intent The query could be a sentence:

22

Page 23: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Information Retrieval

Task In Information Retrieval:

• Given a query

• Retrieve a list of documents related to the query/intent The query could be a picture:

23

Page 24: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Information Retrieval

Task In Information Retrieval:

• Given a query

• Retrieve a list of documents related to the query/intent The query could be an audio/voice:

24

Page 25: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Information Retrieval

Task In Information Retrieval:

• Given a query

• Retrieve a list of documents related to the query

The query could be even anything!!!! Thanks to the contributions by:

• Multimedia

• Natural language processing (NLP)

25

Page 26: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Information Retrieval

Key issues in IR

26

Creation

Utilization Searching & Ranking

Active

Inactive

Semi-Active

Retention/Mining

Disposition

Discard

Using Creating

AuthoringModifying

OrganizingIndexing

StoringRetrieval

DistributionNetworking

AccessingFiltering

Page 27: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Recommender Systems

Page 28: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Outline

• Recommender Systems

Introduction and Applications

Tasks and Evaluations

List of Traditional Recommendation Algorithms

28

Page 29: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Outline

• Recommender Systems

Introduction and Applications

Tasks and Evaluations

List of Traditional Recommendation Algorithms

29

Page 30: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Recommender System (RS)

• RS: item recommendations tailored to user tastes

30

Page 31: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Recommender Systems

31

E-Commerce: Amazon.com, eBay.com, BestBuy, NewEgg

Page 32: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Recommender Systems

32

Online Streaming: Netflix, Pandora, Spotify, Youtube, etc

Page 33: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Recommender Systems

33

Social Media: Facebook, Twitter, Weibo, etc

Page 34: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Recommender Systems

34

• RecSys are able to provide item recommendations

tailored by users’ preferences in the history.

The notion of “item” may vary from domains to domains

E-Commerce: single item, a bundle of items, etc

Movies: each movie, director, actor, movie genre, etc

Music: single track, album, artist, playlist, etc

Travel: tour, flight, hotel, car rental, travel package, etc

Social networks: tweets, user accounts, groups, etc

Page 35: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

How it works

35

Page 36: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

How it works

36

Page 37: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

How it works

37

Page 38: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

How it works

38

Binary FeedbackRatings Reviews Behaviors

• User Preferences

Explicit Implicit

Page 39: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Rating-Based Data Sets

39

T1 T2 T3 T4 T5 T6 T7 T8

U1 4 3 4 2 5

U2 3 4 2 5

U3 4 4 2 2 4

U4 3 5 2 4

U5 2 5 2 4 ? 4

User demographic Information: Age, Gender, Race, Country, etcItem feature information: Movie/Music Genre, Movie director, Music Composer, etc

Page 40: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

How it works

40

Red

Mars

Juras-

sic

Park

Lost

World

2001

Found

ation

Differ-

ence

Engine

Recommender

Systems

User

Profile

Neuro-

mancer2010

Recommendations

Page 41: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Outline

• Recommender Systems

Introduction and Applications

Tasks and Evaluations

List of Traditional Recommendation Algorithms

41

Page 42: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

42

Task and Eval (1): Rating Prediction

User Item Rating

U1 T1 4

U1 T2 3

U1 T3 3

U2 T2 4

U2 T3 5

U2 T4 5

U3 T4 4

U1 T4 3

U2 T1 2

U3 T1 3

U3 T2 3

U3 T3 4

Train

Test

Task: P(U, T) in testing set

Prediction error: e = R(U, T) – P(U, T)

Mean Absolute Error (MAE) =

Other evaluation metrics:• Root Mean Square Error (RMSE)• Coverage• and more …

Page 43: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

43

Task and Eval (1): Rating Prediction

User Item Rating

U1 T1 4

U1 T2 3

U1 T3 3

U2 T2 4

U2 T3 5

U2 T4 5

U3 T4 4

U1 T4 3

U2 T1 2

U3 T1 3

U3 T2 3

U3 T3 4

Train

Test

Task: P(U, T) in testing set

1. Build a model, e.g., P(U, T) = Avg (T)2. Process of Rating Prediction P(U1, T4) = Avg(T4) = (5+4)/2 = 4.5P(U2, T1) = Avg(T1) = 4/1 = 4P(U3, T1) = Avg(T1) = 4/1 = 4P(U3, T2) = Avg(T2) = (3+4)/2 = 3.5P(U3, T3) = Avg(T3) = (3+5)/2 = 43. Evaluation by MetricsMean Absolute Error (MAE) =

ei = R(U, T) – P(U, T)

MAE = (|3 – 4.5| + |2 - 4| + |3 - 4| +|3 – 3.5| + |4 - 4|) / 5 = 1

Page 44: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

44

Task and Eval (2): Top-N Recommendation

User Item Rating

U1 T1 4

U1 T2 3

U1 T3 3

U2 T2 4

U2 T3 5

U2 T4 5

U3 T4 4

U1 T4 3

U2 T1 2

U3 T1 3

U3 T2 3

U3 T3 4

Train

Test

Task: Top-N Items to a user U3

Predicted Rank: T3, T1, T4, T2Real Rank: T3, T2, T1

Then compare the two lists:Precision@N = # of hits/N

Other evaluation metrics:• Recall• Mean Average Precision (MAP)• Normalized Discounted Cumulative Gain (NDCG)• Mean Reciprocal Rank (MRR)• and more …

Page 45: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

45

Task and Eval (2): Top-N Recommendation

User Item Rating

U1 T1 4

U1 T2 3

U1 T3 3

U2 T2 4

U2 T3 5

U2 T4 5

U3 T4 4

U1 T4 3

U2 T1 2

U3 T1 3

U3 T2 3

U3 T3 4

Train

Test

Task: Top-N Items to user U3

1. Build a model, e.g., P(U, T) = Avg (T)2. Process of Rating PredictionP(U3, T1) = Avg(T1) = 4/1 = 4P(U3, T2) = Avg(T2) = (3+4)/2 = 3.5P(U3, T3) = Avg(T3) = (3+5)/2 = 4P(U3, T4) = Avg(T4) = (4+5)/2 = 3.5

Predicted Rank: T3, T1, T4, T2Real Rank: T3, T2, T13. Evaluation Based on the two listsPrecision@N = # of hits/NPrecision@1 = 1/1Precision@2 = 2/2Precision@3 = 2/3

Page 46: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Outline

• Recommender Systems

Introduction and Applications

Tasks and Evaluations

List of Traditional Recommendation Algorithms

46

Page 47: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Traditional Recommendation Algorithms

47

Content-Based Recommendation AlgorithmsThe user will be recommended items similar to the ones the user preferred in the past, such as book/movie recsys

Collaborative Filtering Based Recommendation AlgorithmsThe user will be recommended items that people with similar tastes and preferences liked in the past, e.g., movie recsys

Hybrid Recommendation AlgorithmsCombine content-based and collaborative filtering based algorithms to produce item recommendations.

Page 48: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Context and Context-awareness

Page 49: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Outline

• Context and Context-awareness

What is context and examples

What is context-awareness and examples

Context collections

49

Page 50: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Outline

• Context and Context-awareness

What is context and examples

What is context-awareness and examples

Context collections

50

Page 51: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Factors Influencing Holiday Decisions

51

Page 52: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Example of Contexts

52

• Search in Google (by time)

Page 53: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Example of Contexts

53

• Search in Google Map (by location)

Page 54: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Example of Contexts Beyond Time & Locations

54

• Search in Google Map (by location)

Page 55: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Example of Contexts Beyond Time & Locations

55

• Search in Google Map (by location)

Page 56: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

What is Context?

56

• “Context is any information that can be used to characterize the situation of an entity” by AnindK. Dey, 2001

Page 57: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

What is Context?

57

There are tons of ways to split contexts into

different categories

Page 58: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

What is Context?

58

The most common contextual variables:

Time and Location

User intent or purpose

User emotional states

Devices

Topics of interests, e.g., apple vs. Apple

Others: companion, weather, budget, etc

Usually, the selection/definition of contexts is a domain-specific problem

Page 59: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Outline

• Context and Context-awareness

What is context and examples

What is context-awareness and examples

Context collections

59

Page 60: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Context-Awareness

60

• Context-Awareness = Adapt to the changes of the contextual situations, to build smart applications

• It has been successfully applied to:

– Ubiquitous computing

– Mobile computing

– Information Retrieval

– Recommender Systems

– And so forth…

Page 61: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Example: Smart Home with Remote Controls

61

https://www.youtube.com/watch?v=jB7iuBKcfZw

Page 62: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Example: Smart Home with Context-awareness

62

https://www.youtube.com/watch?v=UQWYRsXkbAM

Page 63: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Content vs Context

63

• Content-Based Approaches

• Context-Driven Applications and Approaches

Page 64: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Content-Based Approaches

64

Page 65: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Context-Driven Applications and Approaches

65

At Cinemawith Friends

At Homewith Family

At Swimming Poolwith Partner

Page 66: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

When Contexts Take Effect?

• Contexts could be useful in different time points

66

Timeline

Past

Context

Current

Context

Future

Context

Most Applications

Historical Data or

Knowledge

Ubiquitous Computing

Context ModelingContext Mining

Context MatchingContext Adaptation

Context PredictionContext Adaptation

Page 67: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Outline

• Context and Context-awareness

What is context and examples

What is context-awareness and examples

Context collections

67

Page 68: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

How to Collect Contexts

• Sensorse.g., the application of smart homes

• User Inputse.g., survey or user interactions

• Inferencee.g., from user reviews

68

Page 69: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

How to Collect Contexts

• Sensors, e.g., the application of smart homes

69

Page 70: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

How to Collect Contexts

• User Inputs, e.g., survey or user interactions

70

Page 71: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

How to Collect Contexts

• Inference, e.g., from user reviews

71

Family Trip

Early Arrival

Season and Family Trip

Page 72: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Short Summary

• Information Overload

• Solution: Information Retrieval (IR)

e.g., Google Search Engine

• Solution: Recommender Systems (RecSys)

e.g., Movie recommender by Netflix

• Context and Context-awareness

e.g., Mobile computing and smart home devices

72

Page 73: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Next

• Coffee Break

– Time: 3:00 PM to 3:30 PM

– Location: Outside Merchants

• Context-awareness in IR and RecSys

• Extended Topics: Trends, Challenges and Future

73

Page 74: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Context-awareness in IR

Page 75: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

75

• Search in Google (by time)

Context-awareness in IR: Examples

Page 76: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

76

• Search in Google Map (by location)

Context-awareness in IR: Examples

Page 77: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Context in IR

77

• Searches should be processed in the context of the information surrounding them, allowing more accurate search results that better reflect the user’s actual intentions. (Finkelstein, 2001)

• Context, in IR, refers to the whole data, metadata, applications and cognitive structures embedded in situations of retrieval or information seeking. (Tamine, et al., 2010)

• These information usually have an impact on the user’s behavior and perception of relevance.

Page 78: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Context in IR

78

Page 79: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Context-awareness in IR

79

Gareth J.F. Jones, 2004

Page 80: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Context-awareness in IR

80

The development of Context-awareness in IR

Interactive and Proactive by Gareth J.F. Jones, 2001

Other Frameworks or ModelsTemporal Models

Semantic Models

Topic Models

Multimedia as inputs: IR based on voice or audios

And so forth…

Page 81: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Terminologies in IR

81

The Author: The author of documents, info provider

The End User: Who releases the queries or Whose context information is captured

Information Recipient: Who finally receive the retrieved information

We assume the end user and information recipient are the same person.

Page 82: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Context-awareness in IR: Interactive Applications

82

Interactive app

• User-driven approach

• Users explicitly issue a request (along with context information) to retrieve relevant documents

• Examples: What are the comfortable hotels near the Omaha Zoo (assume there are no automatic location detectors or sensors)

• Contexts are included in the query; or finer-grained query can be derived from related key words

Page 83: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Context-awareness in IR: Proactive Applications

83

Proactive App• Author-driven approach• Each document is associated with a trigger context. The

documents are retrieved to the user if the trigger context matches user’s current context.

• Example-1: (Location, Time) = trigger contexts for each restaurant; open Yelp, input Chinese dish, Yelp will return a list of Chinese restaurants nearby and valid opening hours at the current moment. [search with queries]

• Example-2: (Location, Time) = trigger contexts for each restaurant; open Yelp, Yelp will deliver a list of Chinese restaurants nearby and valid opening hours at the current moment. [retrieval or recommendation without queries]

Page 84: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Context-awareness in IR

84

Other Frameworks or ModelsTemporal Models

Image retrieval, NYC pictures: old, new? Summer, winter?

Semantic ModelsText retrieval, apple vs Apple?

Topic ModelsAcademic papers retrieval, AI, ML, DM, RecSys?

Multimedia as inputs: IR based on voice or audiosBird singing, which birds? real birds? emotional reactions?

And so forth…

Page 85: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Context-awareness in IR

85

InteractiveUser must give a query

The context information are involved in the user inputs

It is a process from user contexts to relevant documents

ProactiveUser may or may not give a query

Context are captured automatically

It is a process of matching trigger contexts with user contexts

It is a process from documents to users

Page 86: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Context-awareness in RecSys

Page 87: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Outline

• Context-aware Recommendation

Intro: Does context matter?

Definition: What is Context in RecSys?

Collection: Context Acquisition

Selection: How to identify the relevant context?

Context Incorporation

Context Filtering

Context Modeling

Other Challenges and CARSKit87

Page 88: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Non-context vs Context

88

Companion

• Decision Making = Rational + Contextual

• Examples: Travel destination: in winter vs in summer

Movie watching: with children vs with partner

Restaurant: quick lunch vs business dinner

Music: workout vs study

Page 89: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

What is Context?

89

• “Context is any information that can be used to characterize the situation of an entity” by Anind K. Dey, 2001

• Representative Context: Fully Observable and Static• Interactive Context: Non-Fully observable and Dynamic

Page 90: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Interactive Context Adaptation

90

• Interactive Context: Non-fully observable and Dynamic

List of References:

M Hosseinzadeh Aghdam, N Hariri, B Mobasher, R Burke. "Adapting Recommendations to Contextual Changes Using Hierarchical Hidden Markov Models", ACM RecSys 2015

N Hariri, B Mobasher, R Burke. "Adapting to user preference changes in interactive recommendation", IJCAI 2015

N Hariri, B Mobasher, R Burke. "Context adaptation in interactive recommender systems", ACM RecSys 2014

N Hariri, B Mobasher, R Burke. "Context-aware music recommendation based on latent topic sequential patterns", ACM RecSys 2012

Page 91: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

CARS With Representative Context

91

• Observed Context:

Contexts are those variables which may change when a same

activity is performed again and again.

• Examples:

Watching a movie: time, location, companion, etc

Listening to a music: time, location, emotions, occasions, etc

Party or Restaurant: time, location, occasion, etc

Travels: time, location, weather, transportation condition, etc

Page 92: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

What is Representative Context?

92

Activity Structure:

1). Subjects: group of users

2). Objects: group of items/users

3). Actions: the interactions within the activities

Which variables could be context?

1). Attributes of the actions

Watching a movie: time, location, companion

Listening to a music: time, occasions, etc

2). Dynamic attributes or status from the subjects

User emotions

Yong Zheng. "A Revisit to The Identification of Contexts in Recommender Systems", IUI 2015

Page 93: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Context-aware RecSys (CARS)

93

• Traditional RS: Users × Items Ratings

• Contextual RS: Users × Items × Contexts Ratings

Example of Multi-dimensional Context-aware Data set

User Item Rating Time Location Companion

U1 T1 3 Weekend Home Kids

U1 T2 5 Weekday Home Partner

U2 T2 2 Weekend Cinema Partner

U2 T3 3 Weekday Cinema Family

U1 T3 ? Weekend Cinema Kids

Page 94: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Terminology in CARS

94

• Example of Multi-dimensional Context-aware Data set

Context Dimension: time, location, companion

Context Condition: Weekend/Weekday, Home/Cinema

Context Situation: {Weekend, Home, Kids}

User Item Rating Time Location Companion

U1 T1 3 Weekend Home Kids

U1 T2 5 Weekday Home Partner

U2 T2 2 Weekend Cinema Partner

U2 T3 3 Weekday Cinema Family

U1 T3 ? Weekend Cinema Kids

Page 95: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Context Acquisition

95

How to Collect the context and user preferences in contexts?

• By User Surveys or Explicitly Asking for User Inputs

Predefine context & ask users to rate items in these situations;

Or directly ask users about their contexts in user interface;

• By Usage dataThe log data usually contains time and location (at least); User behaviors can also infer context signals;

• By User reviewsText mining or opinion mining could be helpful to infer context information from user reviews

Page 96: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Examples: Context Acquisition (RealTime)

96

Page 97: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Examples: Context Acquisition (Explicit)

97

Page 98: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Examples: Context Acquisition (Explicit)

98

Page 99: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Examples: Context Acquisition (Explicit)

99

Mobile App: South Tyrol Suggests

PersonalityCollection

ContextCollection

Page 100: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

• Inference, e.g., from user reviews

100

Family Trip

Early Arrival

Season and Family Trip

Examples: Context Acquisition (Implicit)

Page 101: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Examples: Context Acquisition (PreDefined)

101

Page 102: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Examples: Context Acquisition (PreDefined)

102

Google Music: Listen Now

Page 103: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Examples: Context Acquisition (User Behavior)

103

Page 104: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Context Relevance and Context Selection

104

Apparently, not all of the context are relevant or influential

• By User Surveyse.g., which ones are important for you in this domain

• By Feature Selectione.g., Principal Component Analysis (PCA)e.g., Linear Discriminant Analysis (LDA)

• By Statistical Analysis or Detection on Contextual RatingsStatistical test, e.g., Freeman-Halton Test Other methods: information gain, mutual information, etc

Reference: Odic, Ante, et al. "Relevant context in a movie recommender system: Users’ opinion vs. statistical detection."

CARS Workshop@ACM RecSys 2012

Page 105: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Context-aware Data Sets

105

Public Data Set for Research Purpose

• Food: AIST Japan Food, Mexico Tijuana Restaurant Data

• Movies: AdomMovie, DePaulMovie, LDOS-CoMoDa Data

• Music: InCarMusic

• Travel: TripAdvisor, South Tyrol Suggests (STS)

• Mobile: Frappe

Frappe is a large data set, others are either small or sparse

Downloads and References:

https://github.com/irecsys/CARSKit/tree/master/context-aware_data_sets

Page 106: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

106

• Once we collect context information, and also identify the most influential or relevant contexts, the next step is to incorporate contexts into the recommender systems.

Context Incorporation

• Traditional RS: Users × Items Ratings

• Contextual RS: Users × Items × Contexts Ratings

Page 107: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

107

• There are three ways to build algorithms for CARS

Context-aware RecSys (CARS)

Page 108: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

108

• Next, we focus on the following CARS algorithms:

Contextual Filtering: Use Context as Filter

Contextual Modeling: Independent vs Dependent

Context-aware RecSys (CARS)

Page 109: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

109

Contextual Filtering

Page 110: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

110

Reduction-based Approach, 2005

Exact and Generalized PreFiltering, 2009

Item Splitting, 2009

User Splitting, 2011

Dimension as Virtual Items, 2011

Differential Context Relaxation, 2012

Differential Context Weighting, 2013

Semantic Contextual Pre-Filtering, 2013

UI Splitting, 2014

Contextual Filtering

Page 111: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

111

• Data Sparsity Problem in Contextual Rating

Differential Context Modeling

User Movie Time Location Companion Rating

U1 Titanic Weekend Home Girlfriend 4

U2 Titanic Weekday Home Girlfriend 5

U3 Titanic Weekday Cinema Sister 4

U1 Titanic Weekday Home Sister ?

Context Matching Only profiles given in <Weekday, Home, Sister>Context Relaxation Use a subset of context dimensions to matchContext Weighting Use all profiles, but weighted by context similarity

Page 112: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

112

• Context Relaxation

Differential Context Modeling

User Movie Time Location Companion Rating

U1 Titanic Weekend Home Girlfriend 4

U2 Titanic Weekday Home Girlfriend 5

U3 Titanic Weekday Cinema Sister 4

U1 Titanic Weekday Home Sister ?

Use {Time, Location, Companion} 0 record matched!Use {Time, Location} 1 record matched!Use {Time} 2 records matched!

Note: a balance is required for relaxation and accuracy

Page 113: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

113

• Context Weighting

Differential Context Modeling

User Movie Time Location Companion Rating

U1 Titanic Weekend Home Girlfriend 4

U2 Titanic Weekday Home Girlfriend 5

U3 Titanic Weekday Cinema Sister 4

U1 Titanic Weekday Home Sister ?

c and d are two contexts. (Two red regions in the Table above.)

σ is the weighting vector <w1, w2, w3> for three dimensions.

Assume they are equal weights, w1 = w2 = w3 = 1.

J(c, d, σ) = # of matched dimensions / # of all dimensions = 2/3

Similarity of contexts is measured by Weighted Jaccard similarity

Page 114: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

114

• Notion of “differential”

In short, we apply different context relaxation and context weighting to each component

Differential Context Modeling

1.Neighbor Selection 2.Neighbor contribution

3.User baseline 4.User Similarity

Page 115: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

115

• WorkflowStep-1: We decompose an algorithm to different components;

Step-2: We try to find optimal context relaxation/weighting:

In context relaxation, we select optimal context dimensions

In context weighting, we find optimal weights for each dimension

• Optimization ProblemAssume there are 4 components and 3 context dimensions

Differential Context Modeling

1 2 3 4 5 6 7 8 9 10 11 12

DCR 1 0 0 0 1 1 1 1 0 1 1 1

DCW 0.2 0.3 0 0.1 0.2 0.3 0.5 0.1 0.2 0.1 0.5 0.2

1st 2nd 3rd 4th

Page 116: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

116

• Optimization Approach Particle Swarm Optimization (PSO)

Genetic Algorithms

Other non-linear approaches

Differential Context Modeling

Fish Birds Bees

Page 117: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

117

• How PSO works?

Differential Context Modeling

Swarm = a group of birds

Particle = each bird ≈ search entity in algorithm

Vector = bird’s position in the space ≈ Vectors we need in DCR/DCW

Goal = the distance to location of pizza ≈ prediction error

So, how to find goal by swam intelligence?

1.Looking for the pizza

Assume a machine can tell the distance

2.Each iteration is an attempt or move

3.Cognitive learning from particle itself

Am I closer to the pizza comparing with

my “best ”locations in previous history?

4.Social Learning from the swarm

Hey, my distance is 1 mile. It is the closest!

. Follow me!! Then other birds move towards here.

DCR – Feature selection – Modeled by binary vectors – Binary PSO

DCW – Feature weighting – Modeled by real-number vectors – PSO

Page 118: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

118

• Summary

Pros: Alleviate data sparsity problem in CARS

Cons: Computational complexity in optimizationCons: Local optimum by non-linear optimizer

Our Suggestion:

We may just run these optimizations offline to find optimal context relaxation or context weighting solutions; And those optimal solutions can be obtained periodically;

Differential Context Modeling

Page 119: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

119

Contextual Modeling

Page 120: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

120

Tensor Factorization, 2010

Context-aware Matrix Factorization, 2011

Factorization Machines, 2011

Deviation-Based Contextual Modeling, 2014

Similarity-Based Contextual Modeling, 2015

Contextual Modeling

Page 121: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

121

Independent Contextual Modeling(Tensor Factorization)

Page 122: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

122

• Tensor Factorization

Independent Contextual Modeling

Multi-dimensional space: Users × Items × Contexts Ratings

Each context variable is modeled as an individual and independent dimension in addition to user & item dims.

Thus we can create a multidimensional space, where rating is the value in the space.

Page 123: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

123

• Tensor Factorization (Optimization)

1).By CANDECOMP/PARAFAC (CP) Decomposition

Independent Contextual Modeling

Multi-dimensional space: Users × Items × Contexts Ratings

Page 124: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

124

• Tensor Factorization (Optimization)

2).By Tucker Decomposition

Independent Contextual Modeling

Multi-dimensional space: Users × Items × Contexts Ratings

Page 125: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

125

• Tensor Factorization

Pros: Straightforward, easily to incorporate contexts into the model

Cons: 1). Ignore the dependence between contexts and user/item dims

2). Increased computational cost if more context dimensions

There are some research working on efficiency improvement on TF,such as reusing GPU computations, and so forth…

Independent Contextual Modeling

Page 126: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

126

Dependent Contextual Modeling(Deviation-Based v.s. Similarity-Based)

Page 127: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

127

• Dependence between Every two Contexts

Deviation-Based: rating deviation between two contexts

Similarity-Based: similarity of rating behaviors in two contexts

Dependent Contextual Modeling

Page 128: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

128

• Notion: Contextual Rating Deviation (CRD)

CRD how user’s rating is deviated from context c1 to c2?

CRD(D1) = 0.5 Users’ rating in Weekday is generally higher than users’ rating at Weekend by 0.5

CRD(D2) = -0.1 Users’ rating in Cinema is generally lower than users’ rating at Home by 0.1

Deviation-Based Contextual Modeling

Context D1: Time D2: Location

c1 Weekend Home

c2 Weekday Cinema

CRD(Di) 0.5 -0.1

Page 129: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

129

• Notion: Contextual Rating Deviation (CRD)

CRD how user’s rating is deviated from context c1 to c2?

Assume Rating (U, T, c1) = 4

Predicted Rating (U, T, c2) = Rating (U, T, c1) + CRDs

= 4 + 0.5 -0.1 = 4.4

Deviation-Based Contextual Modeling

Context D1: Time D2: Location

c1 Weekend Home

c2 Weekday Cinema

CRD(Di) 0.5 -0.1

Page 130: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

130

• Build a deviation-based contextual modeling approach

Assume Ø is a special situation: without considering context

Assume Rating (U, T, Ø) = Rating (U, T) = 4

Predicted Rating (U, T, c2) = 4 + 0.5 -0.1 = 4.4

Deviation-Based Contextual Modeling

Context D1: Time D2: Location

Ø UnKnown UnKnown

c2 Weekday Cinema

CRD(Di) 0.5 -0.1

In other words, F(U, T, C) = P(U, T) + 𝑖=0𝑁 𝐶𝑅𝐷(𝑖)

Page 131: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

131

• Build a deviation-based contextual modeling approach

Note: P(U, T) could be a rating prediction by any traditional recommender systems, such as matrix factorization

Deviation-Based Contextual Modeling

Simplest model: F(U, T, C) = P(U, T) + 𝑖=0𝑁 𝐶𝑅𝐷(𝑖)

User-personalized model: F(U, T, C) = P(U, T) + 𝑖=0𝑁 𝐶𝑅𝐷(𝑖, 𝑈)

Item-personalized model: F(U, T, C) = P(U, T) + 𝑖=0𝑁 𝐶𝑅𝐷(𝑖, 𝑇)

Page 132: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

132

• Build a similarity-based contextual modeling approach

Assume Ø is a special situation: without considering context

Assume Rating (U, T, Ø) = Rating (U, T) = 4

Predicted Rating (U, T, c2) = 4 × Sim(Ø, c2)

Similarity-Based Contextual Modeling

Context D1: Time D2: Location

Ø UnKnown UnKnown

c2 Weekday Cinema

Sim(Di) 0.5 0.1

In other words, F(U, T, C) = P(U, T) × Sim(Ø, C)

Page 133: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

133

• Challenge: how to model context similarity, Sim(c1,c2)

We propose three representations:

• Independent Context Similarity (ICS)

• Latent Context Similarity (LCS)

• Multidimensional Context Similarity (MCS)

Similarity-Based Contextual Modeling

Page 134: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

134

• Sim(c1, c2): Independent Context Similarity (ICS)

𝑆𝑖𝑚 c1, 𝑐2 = 𝑖=1𝑁 𝑠𝑖𝑚(𝐷𝑖) = 0.5 × 0.1 = 0.05

Similarity-Based Contextual Modeling

Context D1: Time D2: Location

c1 Weekend Home

c2 Weekday Cinema

Sim(Di) 0.5 0.1

𝐺𝑒𝑛𝑒𝑟𝑎𝑙𝑙𝑦, 𝐼𝑛 𝐼𝐶𝑆: 𝑆𝑖𝑚 c1, 𝑐2 = 𝑖=1𝑁 𝑠𝑖𝑚(𝐷𝑖)

Weeend Weekday Home Cinema

Weekend 1 b — —

Weekday a 1 — —

Home — — 1 c

Cinema — — d 1

Page 135: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

135

• Sim(c1, c2): Latent Context Similarity (LCS)

In training, we learnt (home, cinema), (work, cinema)

In testing, we need (home, work)

Similarity-Based Contextual Modeling

𝐺𝑒𝑛𝑒𝑟𝑎𝑙𝑙𝑦, 𝐼𝑛 𝐿𝐶𝑆: 𝑆𝑖𝑚 c1, 𝑐2 = 𝑖=1𝑁 𝑠𝑖𝑚(𝐷𝑖)

𝑆𝑖𝑚 𝐷𝑖 = 𝑑𝑜𝑡𝑃𝑟𝑜𝑑𝑢𝑐𝑡 (𝑉𝑖1, 𝑉𝑖2)

f1 f2 … … … … fN

home 0.1 -0.01 … … … … 0.5

work 0.01 0.2 … … … … 0.01

cinema 0.3 0.25 … … … … 0.05

VectorRepresentation

Page 136: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

136

• Sim(c1, c2): Multidimensional Context Similarity (MCS) Each context condition is an individual axis in the space.

For each axis, there are only two values: 0 and 1.

1 means this condition is selected; otherwise, not selected.

When value is 1, each condition is associated with a weight

c1 = <Weekday, Cinema, with Kids>c2 = <Weekend, Home, with Family>

They can be mapped as two points in the space

Similarity-Based Contextual Modeling

𝐼𝑛 𝑀𝐶𝑆: 𝐷𝑖𝑠𝑆𝑖𝑚 c1, 𝑐2 = distance between two point

Page 137: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

137

Similarity-Based Contextual Modeling

Similarity-Based CAMF:

Similarity-Based CSLIM:

• Build algorithms based on traditional recommender

𝐼𝑛 𝐼𝐶𝑆: 𝑆𝑖𝑚 c1, 𝑐2 = 𝑖=1𝑁 𝑠𝑖𝑚(𝐷𝑖)

𝐼𝑛 𝐿𝐶𝑆: 𝑆𝑖𝑚 c1, 𝑐2 = 𝑖=1𝑁 𝑠𝑖𝑚 𝐷𝑖 , 𝑠𝑖𝑚 𝐷𝑖 𝑖𝑠 𝑑𝑜𝑡𝑃𝑟𝑜𝑑𝑢𝑐𝑡

𝐼𝑛 𝑀𝐶𝑆:𝐷𝑖𝑠𝑠𝑖𝑚𝑖𝑙𝑎𝑟𝑖𝑡𝑦 𝑖𝑠 𝑑𝑖𝑠𝑡𝑎𝑛𝑐𝑒, 𝑠𝑢𝑐ℎ 𝑎𝑠 𝐸𝑢𝑐𝑙𝑖𝑑𝑒𝑎𝑛 𝑑𝑖𝑠𝑡𝑎𝑛𝑐𝑒

Page 138: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

138

CARSKit: Recommendation Library

Page 139: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

139

Recommendation Library

• Motivations to Build a Recommendation Library

1). Standard Implementations for popular algorithms

2). Standard platform for benchmark or evaluations

3). Helpful for both research purpose and industry practice

4). Helpful as tools in teaching and learning

Page 140: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

140

Recommendation Library

There are many recommendation library for traditional recommendation.Users × Items Ratings

Page 141: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

141

CARSKit: A Java-based Open-sourceContext-aware Recommendation Library

CARSKit: https://github.com/irecsys/CARSKitUsers × Items × Contexts Ratings

User Guide: http://arxiv.org/abs/1511.03780

Page 142: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

142

CARSKit: A Short User Guide

1. Download the JAR library, i.e., CARSKit.jar2. Prepare your data

3. Setting: setting.conf

4. Run: java –jar CARSKit.jar –c setting.conf

Page 143: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

143

CARSKit: A Short User Guide

Sample of Outputs: Data Statistics

Page 144: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

144

CARSKit: A Short User Guide

Sample of Outputs:

1). Results by Rating Prediction TaskFinal Results by CAMF_C, MAE: 0.714544, RMSE: 0.960389, NAME: 0.178636, rMAE: 0.683435, rRMSE: 1.002392, MPE: 0.000000, numFactors: 10, numIter: 100, lrate: 2.0E-4, maxlrate: -1.0, regB: 0.001, regU: 0.001, regI: 0.001, regC: 0.001, isBoldDriver: true, Time: '00:01','00:00‘

2). Results by Top-N Recommendation TaskFinal Results by CAMF_C, Pre5: 0.048756,Pre10: 0.050576, Rec5: 0.094997, Rec10: 0.190364, AUC: 0.653558, MAP: 0.054762, NDCG: 0.105859, MRR: 0.107495, numFactors: 10, numIter: 100, lrate: 2.0E-4, maxlrate: -1.0, regB: 0.001, regU: 0.001, regI: 0.001, regC: 0.001, isBoldDriver: true, Time: '00:01','00:00'

Page 145: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

145

Example of Experimental Results

Page 146: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

146

Example of Experimental Results

Page 147: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Extended Topics:Trends, Challenges & Future

Page 148: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

148

Challenges

• There could be many other challenges in context-awareness in IR and RecSys:

Numeric v.s. Categorical Context Information

Explanations by Context

New User Interfaces and Interactions

User Intent Predictions or References in IR and RecSys

Cold-start and Data Sparisty Problems in CARS

Page 149: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

149

Challenges: Numeric Context

• List of Categorical Context

Time: morning, evening, weekend, weekday, etc

Location: home, cinema, work, party, etc

Companion: family, kid, partner, etc

• How about numeric contextTime: 2016, 6:30 PM, 2 PM to 6 PM (time-aware recsys)Temperature: 12°C, 38°CPrinciple component by PCA: numeric values

Page 150: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

150

Challenges: Explanation

• Recommendation Using social networks (By Netflix)

The improvement is not significant;

Unless we explicitly explain it to the end users;

• IR and RecSys Using context (Open Research)Similar thing could happen to context-aware IR & recsys;

How to use contexts to explain information filtering;

How to design new user interface to explain;

How to introduce user-centric evaluations;

Page 151: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

151

Challenges: User Interface

• Potential Research Problems in User Interface

New UI to collect context;

New UI to interact with users friendly and smoothly;

New UI to explain context-aware IR and RecSys;

New UI to avoid debates on user privacy;

User privacy problems in context collection & usage

Page 152: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

152

Challenges: Cold-Start and Data Sparsity

• Cold-start Problems

Cold-start user: no rating history by this userCold-start item: no rating history on this itemCold-start context: no rating history within this context

• Solution: Hybrid Method by Matthias Braunhofer, et al.

Page 153: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

153

Challenges: User Intent

• User Intent could be the most influential contexts

How to better predict that

How to better design UI to capture that

How to balance user intent and limitations in resources

Page 154: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

154

Trends and Future

• Context-awareness enable new applications: context suggestion, or context-driven UI/Applications

Context Suggestion

Page 155: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Context Suggestion

155

• Task: Suggest a list of contexts to users (on items)

Context Rec

Contextual RecTraditional Rec

Page 156: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

156

Context Suggestion: Motivations

• Motivation-1: Maximize user experience

User Experience (UX) refers to a person's emotions and

attitudes about using a particular product, system or

service.

Page 157: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

157

Context Suggestion: Motivations

• Motivation-1: Maximize user experience

It is not enough to recommend items only

Page 158: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Zoo Parks in San Diego, USA

158

• San Diego Zoo • San Diego Zoo Safari Park

Page 159: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Zoo Parks in San Diego, USA

159

Page 160: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

160

Context Suggestion: Motivations

• Motivation-2: Contribute to Context Collection

Predefine contexts and suggest them to users

Page 161: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

161

Context Suggestion: Motivations

• Motivation-3: Connect with Context-aware RecSys

User’s actions on context is a context-query to system

Page 162: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

162

References

L Baltrunas, M Kaminskas, F Ricci, et al. Best usage context prediction for music tracks. CARS@ACM RecSys, 2010

Y Zheng, B Mobasher, R Burke. Context Recommendation Using Multi-label Classification. IEEE/WIC/ACM WI, 2014

Y Zheng. Context Suggestion: Solutions and Challenges. ICDM Workshop, 2015

Y Zheng. Context-Driven Mobile Apps Management and Recommendation. ACM SAC, 2016

Yong Zheng, Bamshad Mobasher, Robin Burke. “User-Oriented Context Suggestion“, ACM UMAP, 2016

Page 163: Tutorial: Context-awareness In Information Retrieval and Recommender Systems

Tutorial: Context-Awareness In Information Retrieval and Recommender Systems

Yong ZhengSchool of Applied Technology

Illinois Institute of Technology, Chicago

The 16th IEEE/WIC/ACM Conference on Web Intelligence, Omaha, USA