Context-Aware Computing Sfide ed Opportunità Francesco Ricci Free University of Bozen-Bolzano fricci@unibz.it
Content p Paradox of choice p Personalization p Contextualization p Recommender system p Examples p Issues and problems p Questions 2
Explosion of Choice p A trip to a local supermarket : n 85 different varieties and brands of crackers. n 285 varieties of cookies. n 165 varieties of “ juice drinks ” n 75 iced teas n 275 varieties of cereal n 120 different pasta sauces n 80 different pain relievers n 40 options for toothpaste n 95 varieties of snacks (chips, pretzels, etc.) n 61 varieties of sun tan oil and sunblock n 360 types of shampoo, conditioner, gel, and mousse. n 90 different cold remedies and decongestants. n 230 soups, including 29 different chicken soups n 175 different salad dressings and if none of them suited, 15 extra-virgin olive oils and 42 vinegars and make one ’ s own
New Domains for Choice p Telephone Services p Retirement Pensions p Medical Care p Choosing Beauty p Choosing how to work p Choosing how to love p Choosing how to be
Choice and Well-Being p We have more choice , and presumably more freedom, autonomy, and self determination, than ever before p It seems that increased choice improves well- being n added options can only make us better off: those who care will benefit, and those who do not care can always ignore the added options p Various assessment of well-being have shown that increased affluence have accompanied by decreased well-being .
Personalization p “If I have 3 million customers on the Web, I should have 3 million stores on the Web” n Jeff Bezos , CEO and founder, Amazon.com n Degree in Computer Science n $34.2 billion (net worth), ranked no. 15 in the Forbes list of the America's Wealthiest 6 People
Amazon.it 7
Movie Recommendation – YouTube Recommendations account for about 60% of all video clicks from 8 the home page.
Consumer Attitudes 9
The Long Tail p Netflix (catalog of over 100,000 movie titles) rents a large volume of less popular movies in addition to the substantial business it does renting hits. p The Long Tail: the economic model in which the market for non-hits (typically large numbers of low-volume items) could be significant and sometimes even greater than the market for big hits (typically small numbers of high-volume items). 10
Recommendations can be wrong p Recommenders tend to recommend items similar to those browsed or purchased in the past 11
Context-Aware Computing p Gartner Top 10 strategic technology trends for IT p Context-aware computing is a style of computing in which situational and environmental information about people, places and things is used to anticipate immediate needs and proactively offer enriched, situation-aware and usable content, functions and experiences. http://www.gartner .com/it-glossary/context-aware-computing-2 12
Google Now 13 https://www.google.com/landing/now/
Types of Context - Mobile p Physical context n time, position, and activity of the user, [Fling, 2009] weather, light, and temperature ... p Social context n the presence and role of other people around the user p Interaction media context n the device used to access the system and the type of media that are browsed and personalized (text, music, images, movies, …) p Modal context n The state of mind of the user, the user’s goals, mood, experience, and cognitive capabilities. 14
Mobile Usage Users complete information tasks by using multiple devices Share of Browser-Based Page Traffic by Hour for Computer , Smartphone and Tablet Platforms Source: comScore Device 15 Essentials, U.S., Monday, Jan. 21, 2013
Goal p Recommend items that are good for you! n relevant n improve well being n rational choices n optimal 16
Movie rating data Training data Test data user movie date user movie date score score 1 21 5/7/02 1 1 62 1/6/05 ? 1 213 8/2/04 5 1 96 9/13/04 ? 2 345 3/6/01 4 2 7 8/18/05 ? 2 123 5/1/05 4 2 3 11/22/05 ? 2 768 7/15/02 3 3 47 6/13/02 ? 3 76 1/22/01 5 3 15 8/12/01 ? 4 45 8/3/00 4 4 41 9/1/00 ? 5 568 9/10/05 1 4 28 8/27/05 ? 5 342 3/5/03 2 5 93 4/4/05 ? 5 234 12/28/00 2 5 74 7/16/03 ? 6 76 8/11/02 5 6 69 2/14/04 ? 6 56 6/15/03 4 6 83 10/3/03 ? 17
Matrix of ratings Items Users 18
Latent Factor Models serious Braveheart The Color Amadeus Purple Lethal Sense and Weapon Sensibility Ocean ’ s 11 Geared Geared towards towards males females Dave The Lion King Dumb and Dumber The Princess Independence Diaries Day Gus escapist 19
Semantic contextual pre-filtering q Key idea: reuse ratings acquired in similar contexts ≠ semantic similarities ≈ Ratings predicted Prediction rating filtering model "similar context" in-context ratings ratings target context 20
South Tyrol Suggest (STS) • A mobile Android context-aware RS that recommends places of interests (POIs) from a total of 27,000 POIs in South Tyrol region • STS computes rating predictions for all POIs using the personality of the users, the ratings, and 14 contextual factors, such as: weather forecast, mood, budget, and travel goal. Openness Agreeableness Extraversion Big Five Personality Traits Conscientious- Neuroticism ness
Food Advisor for a Family
Problems and Issues p Cold Start (new user and new item) - old items are less interesting p Learning to interact p Measuring p Filter Bubble p How much to personalize p When to contextualize p How to deliver contextualized content? p Multiple devices (synchronization) 23
Questions?
Context-Awareness Users can experience items differently depending • on the current context (e.g., season, weather, temperature, mood) Needs to be considered in the personalization • process (= context-aware system)
Factors influencing Holiday Decision Internal to the tourist External to the tourist Personal Availability of Motivators products Advice of travel Personality agents Disposable Income Information obtained from tourism Health organization and media Family Word-of-mouth commitments recommendations Decision Past experience Political restrictions: visa, terrorism, Works commitments Hobbies and Health problems interests Knowledge of Special promotion potential and offers holidays Lifestyle Attitudes, Climate opinions and [Swarbrooke & Horner, 2006] perceptions
Active Learning What ? Why ? • • It is requesting and trying to collect The more ratings, the better the more and better ratings from the users recommendation quality before offering recommendations • But users tend to give only few ratings • And not all the given ratings are equally useful How ? • Selectively, choosing a set of items and presenting them to the users and asking the users to rate
Context and Preferences Expected Context Preferences Experienced Remembered Reasoning 28
Recommend
More recommend
