Contextual Recommendation of Social Updates, a tag-based framework

Contextual Recommendation of Social Updates a tag-based framework Adrien JOLY PhD Candidate, supervisor: Prof. Pierre MARET Alcatel-Lucent Bell Labs France + INSA-Lyon, LIRIS, UMR5205 [email_address] / [email_address]

Agenda of this presentation Motivation — Awareness and information overload Approach — Context-based filtering Framework — Contextual tag clouds Evaluation — Perceived relevance Conclusion & future work

Motivation Approach Framework Evaluation Conclusion Introduction to Awareness Awareness is the state or ability to perceive, to feel, or to be conscious of events, objects or sensory patterns […] without necessarily implying understanding. [wikipedia.org] Social Awareness current/recent people activities, moods, availability, status… [Dourish, Ericksson, Gutwin…] Context Awareness location, surrounding environment… [Dey’2000]

Motivation Approach Framework Evaluation Conclusion Web « 2.0 » social / communication tools Social Networking Platforms increase Social Awareness

Motivation Approach Framework Evaluation Conclusion Web « 2.0 » social / communication tools Social Networking Platforms increase Social Awareness … through Social Updates

Motivation Approach Framework Evaluation Conclusion Web « 2.0 » social / communication tools Social Networking Platforms increase Social Awareness But it can steal a lot of attention  productivity loss

Motivation Approach Framework Evaluation Conclusion Our proposal Filter “ Aware” user Activities / Status Updates / Contacts Needed Social updates and productive

Agenda of this presentation Motivation Approach Framework Evaluation Conclusion

Motivation Approach Framework Evaluation Conclusion Filtering possibilities Motivated goal: Filter social network updates to enable awareness without information overload What criteria should we adopt to find the most relevant updates ? Popularity ? (most spread updates) Response rate ? (most commented updates) Content-based filtering ? (according to preferences) [Budzik’2000, Bauer’2001] Collaborative filtering ? (according to similar ratings) [Agosto’2005, Bielenberg’2005] Similarity of context

Motivation Approach Framework Evaluation Conclusion Similarity of context, our hypothesis C A is the context of a user U A sharing a piece of information I A . C X is the context of a user U X that is a potential recipient of this information. Hypothesis: I A is relevant to U X if C A is similar to C X A A = Travel in Asia U A = Alice I A = « Check out my amazing picture ! » A B = Working Java U B = Bob I B = « What database should I use ? » A C = Browsing map U C = Christine I C = « Looking for holiday locations… »

Motivation Approach Framework Evaluation Conclusion Similarity of context, our hypothesis C A is the context of a user U A sharing a piece of information I A . C X is the context of a user U X that is a potential recipient of this information. Hypothesis: I A is relevant to U X if C A is similar to C X C A = Travel, Asia C C = Travel C B = Java Dev. A A = Travel in Asia U A = Alice A B = Working Java U B = Bob I B = « What database should I use ? » A C = Browsing map U C = Christine I C = « Looking for holiday locations… » Similar context: travel No relevant match for this context I A = « Check out my amazing picture ! »

Motivation Approach Framework Evaluation Conclusion What is context ? Context [Dey, 2001] : « any information that can be used to characterize the situation of an entity » From physical sensors: From computer-based actions: Location Surrounding people Other sensors Communication history Web browsing history Document history

Motivation Approach Framework Evaluation Conclusion From sensors to applications Context sensors Applications Interpretation Acquisition db Usual representation scheme for context information: Ontology-based / semantic Requires ont. modeling Lack of semantic data Complex to manipulate Scaling issues Context Management Framework

Motivation Approach Framework Evaluation Conclusion From sensors to applications Context Management Framework Context sensors Social Applications Interpretation Acquisition db Proposed representation scheme for context information: Contextual tag clouds Easy to browse Easy to edit Simple & interoperable Crowds-friendly Updates Paris Notre-Dame Café Cloudy Crowded Sitting with:Pierre

Motivation Approach Framework Evaluation Conclusion Context Aggregation and Filtering process Social updates Aggregator Sniffers Notifier Filter User Actions and tags Contextual clouds Notifications Context Interfaces Abstraction and weighting Services

Motivation Approach Framework Evaluation Conclusion Context Aggregation and Filtering process –- in the enterprise Social updates Aggregator Sniffers Notifier Filter User Actions and tags Contextual clouds Notifications Context Interfaces Abstraction and weighting Services

Motivation Approach Framework Evaluation Conclusion How to synthesize the contextual tag cloud from web browsing ? The user opens a web page…

Motivation Approach Framework Evaluation Conclusion How to synthesize the contextual tag cloud from web browsing ? Low level and static author description Automatic content analysis Mining semantic concepts from content People-entered tags (wisdom of crowds) 1) URL is sent to the Context Aggregator 2) Content is analyzed by enhancers (including web services)

Motivation Approach Framework Evaluation Conclusion Contextual Tag Clouds, vector space model and algebra Sample tag cloud R : (normalized) Aggregation of a set V of normalized Tag Clouds  normalized sum: Relevance of Tag Cloud R with S  cosine similarity: 0.1 0.1 0.3 0.5 « Discount » « Flight » « Asia » « Travel »

Motivation Approach Framework Evaluation Conclusion Contextual Tag Clouds, extraction and enhancement functions 1. Extracting weighted terms from: Resource Metadata Title Keywords Description Parameters = 50 = 10 = 1

Motivation Approach Framework Evaluation Conclusion Contextual Tag Clouds, extraction and enhancement functions 2+3. Extracting weighted terms from: 2. Search Query ambient, awareness 3. Resource Location video, all, alcatel-Lucent

Motivation Approach Framework Evaluation Conclusion Contextual Tag Clouds, extraction and enhancement functions Extracting weighted terms from: Social Annotations w poster = 11, w work = 11, w gtd = 10, w done = 10, w inspiration = 7, …

Motivation Approach Framework Evaluation Conclusion Contextual Tag Clouds, extraction and enhancement functions Extracting weighted terms from: Semantic Analysis of content MIT, Tim Berners-Lee, …

Motivation Approach Framework Evaluation Conclusion Requirements and plan Hypothesis: Recommended social updates are relevant when users’ contexts are similar To evaluate: Tag cloud similarity for relevance ranking Relevance of social updates to the context of their posting Experimentation plan: (1 week)  1 tag cloud every 10 minutes  2 personalized surveys per user

Motivation Approach Framework Evaluation Conclusion From browsing activity to social matching Temporal indexing period = 10 mn. Common tags: JAVA, DEV Common tags: TRAVEL  Recommend u5’s social update to u1  Recommend u3’s social update to u7

Motivation Approach Framework Evaluation Conclusion Survey #1 … and 3 social updates with various relevance scores, for each context upd1 upd2 1 2 3 4 1 2 3 4 Survey #1 : For each user, 5 personal contextual clouds are proposed…

Motivation Approach Framework Evaluation Conclusion Survey #1 results 1/2  rarity of good matches (few participants  few common tags)

Motivation Approach Framework Evaluation Conclusion Survey #1 results 2/2  Accuracy = 72% (based on MAE between relevance scores and ratings) Accuracy

Motivation Approach Framework Evaluation Conclusion Survey #2 Survey #2 : For each user’s social update, Evaluation of relevance between social updates and context of posting rating Results Average relevance rating: 50.3% (over 59 social updates), including: - 71% for social bookmark notifications - 38% for tweets ( ≈ 41% of “me now” statuses on twitter [Naaman’2010]) 1 2 3 4

Motivation Approach Framework Evaluation Conclusion Contribution Goal : Increase awareness, reduce information overload Proposition : Use contextual information to rank relevance of social updates Approach : Tag-based context representation, instead of ontology-based Findings (using web browsing activity as context) : Encouraging results: 72% accuracy Half social updates are relevant to web browsing context, depending on nature

Motivation Approach Framework Evaluation Conclusion Future work Improve quality of contextual tag clouds Semantic analysis, clustering, and filtering of tags Dynamic weights (based on time) Deeper study of social updates Relevance factors between specific social update and contextual properties Gather context from other sources Additional types of documents (e.g. emails, PDF/word documents…) Physical context information Develop a contextual tag cloud manipulation interface (HSI) Graphical extension, multidimensional/hierarchical tag cloud ? How to edit tags and their weights ?

www.alcatel-lucent.com Thank you for your attention! Your questions are welcome 

Contextual Recommendation of Social Updates, a tag-based framework

More Related Content

What's hot (20)

Viewers also liked (6)

Similar to Contextual Recommendation of Social Updates, a tag-based framework (20)

Recently uploaded (20)

Contextual Recommendation of Social Updates, a tag-based framework

Editor's Notes