Reading the Correct History? Modeling Temporal Intention in Resource Sharing

62
Reading the Correct History? Modeling Temporal Intention in Resource Sharing Hany SalahEldeen & Michael Nelson Reading the Correct History? Hany M. SalahEldeen & Michael L. Nelson Old Dominion University Department of Computer Science Web Science and Digital Libraries Lab.

description

Presentation at JCDL 2013, Indianapolis, Indiana

Transcript of Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Page 1: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Reading the Correct History? Modeling Temporal Intention in

Resource Sharing

Hany SalahEldeen & Michael Nelson Reading the Correct History?

Hany M. SalahEldeen & Michael L. Nelson

Old Dominion University Department of Computer Science

Web Science and Digital Libraries Lab.

Page 2: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Hany SalahEldeen & Michael Nelson 1 Reading the Correct History?

• We share web pages

What I share might not be what my readers read Possible Scenario:

• Web pages change

• Readers explore shared pages

Page 3: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Motivation

A temporal inconsistency can arise in the intention of the author regarding the state of the resource between the

tweet time and the read time…

Hany SalahEldeen & Michael Nelson 2 Reading the Correct History?

Can we detect and model this difference in intention?

Page 4: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

The game plan

Hany SalahEldeen & Michael Nelson 3 Reading the Correct History?

Problem Illustration

Training data collection attempts

The TIRM model

Ground truth validation

Data collection

Feature extraction and modeling

Model evaluation

Page 5: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Example: Obama’s press conference on 14th of Jan 2013

Hany SalahEldeen & Michael Nelson 4 Reading the Correct History?

Page 6: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Clicking on the link in the tweet …

Hany SalahEldeen & Michael Nelson 5 Reading the Correct History?

Page 7: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Using the Twitter expanded interface

Hany SalahEldeen & Michael Nelson 6 Reading the Correct History?

The attack on the embassy was in February 2013

Page 8: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Problem: There is an inconsistency between what the tweet’s author intended

to share at time ttweet

and what the reader might actually read upon clicking on the link at time tclick .

Hany SalahEldeen & Michael Nelson 7 Reading the Correct History?

Page 9: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Hany SalahEldeen & Michael Nelson 8 Reading the Correct History?

Implication: Since tweets are considered the first draft of history… the historical

integrity of the tweets could be compromised.

Page 10: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Solution: Detect the correct intention

Hany SalahEldeen & Michael Nelson 9 Reading the Correct History?

Option 1 Option 2 Option 3

Page 11: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

The game plan

Hany SalahEldeen & Michael Nelson Reading the Correct History?

Problem Illustration

Training data collection attempts

The TIRM model

Ground truth validation

Data collection

Feature extraction and modeling

Model evaluation

Page 12: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Amazon’s Mechanical Turk (MT) • Crowdsourcing Internet marketplace

• Co-ordinates the use of human intelligence to perform tasks that computers are currently unable to do.*

Hany SalahEldeen & Michael Nelson 10 Reading the Correct History?

* http://en.wikipedia.org/wiki/Amazon_Mechanical_Turk

Page 13: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Goal: Collect user intention data via MT

Hany SalahEldeen & Michael Nelson 11

Reading the Correct History?

Tweets dataset Intention Classification Tasks User Intention Data

Classifier

Train

• Problem:

– It is not as easy as it seems!

Page 14: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

How not to classify temporal intention 101

• Given a tweet, is the intended state of the link is in:

Hany SalahEldeen & Michael Nelson 12 Reading the Correct History?

past state? current state? No information?

Page 15: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Ground truth collection

• A dataset of 100 tweets classified by:

– Our Web Science and Digital Libraries (WS-DL) research group members

– MT workers

Hany SalahEldeen & Michael Nelson 13 Reading the Correct History?

Page 16: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

The agreement was very low…

• Reliability of agreement between:

– WS-DL members = Fleiss’ ϰ = 0.14

– MT workers = Fleiss’ ϰ = 0.07

• Inter-rater agreement between the collective WS-DL members and MT workers = Cohen’s ϰ = 0.04

Slight agreement

Hany SalahEldeen & Michael Nelson 14 Reading the Correct History?

Page 17: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

So we removed the guessing part: • The tweet is presented along with the two snapshots:

Hany SalahEldeen & Michael Nelson 15 Reading the Correct History?

at ttweet at tclick

Page 18: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

… and classified the 100 tweets again

• Via a face to face meeting with WS-DL members.

• Resubmitted the new experiment to MT.

Hany SalahEldeen & Michael Nelson 16 Reading the Correct History?

Page 19: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

The tweet, current and past snapshots

Hany SalahEldeen & Michael Nelson 17 Reading the Correct History?

Past Version Current Version

Page 20: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

The results remained very low

• For 9 MT assignments per tweet:

– If we allowed 4-5 splits we have 58% match with WS-DL.

– If we allowed 3-6 splits or better we got 31% match

Which is worse that flipping a coin!

Hany SalahEldeen & Michael Nelson 18 Reading the Correct History?

Page 21: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Observations

• Assigning a temporal intention is not a trivial task.

• MT workers are accustomed to more straightforward tasks.

• The concept of “time on the web” is foreign to MT workers.

Hany SalahEldeen & Michael Nelson 19 Reading the Correct History?

Page 22: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

The game plan

Hany SalahEldeen & Michael Nelson Reading the Correct History?

Problem Illustration

Training data collection attempts

The TIRM model

Ground truth validation

Data collection

Feature extraction and modeling

Model evaluation

Page 23: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Idea: We need to transform the problem from intention to

relevance.

Hany SalahEldeen & Michael Nelson 20 Reading the Correct History?

Page 24: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Relevance tasks are simpler

• MT workers are more accustomed to classification tasks and it requires minimum amount of explanation

Is that a cat?

- Yes

- No

Hany SalahEldeen & Michael Nelson 21 Reading the Correct History?

Page 25: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Hany SalahEldeen & Michael Nelson 22 Reading the Correct History?

Temporal Intention Relevancy Model ( TIRM)

Between ttweet and tclick:

The linked resource could have: • Changed • Not changed

The tweet and the linked resource could be: • Still relevant • No longer relevant

Page 26: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Hany SalahEldeen & Michael Nelson 23 Reading the Correct History?

Resource is changed but relevant

• The resource changed • But it is still relevant

Intention: need the current version of the resource at any time

Page 27: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Hany SalahEldeen & Michael Nelson 24 Reading the Correct History?

Relevancy and Intention Mapping

Current

Page 28: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Hany SalahEldeen & Michael Nelson 25 Reading the Correct History?

Resource is changed and not relevant

Intention: need the past version of the resource at any time

• The resource changed • But it is no longer relevant

Page 29: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Past

Hany SalahEldeen & Michael Nelson 26 Reading the Correct History?

Relevancy and Intention Mapping

Current

Page 30: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Hany SalahEldeen & Michael Nelson 27 Reading the Correct History?

Resource is not changed and relevant

Intention: need the past version of the resource at any time

• The resource is not changed • And it is relevant

Page 31: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Past

Hany SalahEldeen & Michael Nelson 28 Reading the Correct History?

Relevancy and Intention Mapping

Current

Past

Page 32: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Hany SalahEldeen & Michael Nelson 29 Reading the Correct History?

Resource is not changed and not relevant

Intention: I am not sure which version of the resource I need

• The resource is not changed • But it is not relevant

Page 33: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Past

Hany SalahEldeen & Michael Nelson 30 Reading the Correct History?

Relevancy and Intention Mapping

Current

Past Not Sure

Page 34: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

The game plan

Hany SalahEldeen & Michael Nelson Reading the Correct History?

Problem Illustration

Training data collection attempts

The TIRM model

Ground truth validation

Data collection

Feature extraction and modeling

Model evaluation

Page 35: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Next step: validation

• MT workers ≡ judgments of the experts (WS-DL members)

Hany SalahEldeen & Michael Nelson 31 Reading the Correct History?

Is the content still relevant to the tweet?

Page 36: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Filtering the results

• We accepted raters with: – At least 1000 accepted HITs

– 95% acceptance rate

• Average completion time = 61 seconds

• We removed:

– Any assignments that took <10 seconds hasty decision

– Low quality repetitive assignments and banned the raters

Hany SalahEldeen & Michael Nelson 32 Reading the Correct History?

Page 37: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Mechanical Turk Workers Vs. Experts

• For 100 tweets, WS-DL members % of agreement :

• Cohen’s ϰ = 0.854 almost perfect agreement

Hany SalahEldeen & Michael Nelson 33 Reading the Correct History?

Agreement in three or more votes 93%

Agreement in four or more votes 80%

Agreement with all five votes 60%

Page 38: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

The game plan

Hany SalahEldeen & Michael Nelson 34 Reading the Correct History?

Problem Illustration

Training data collection attempts

The TIRM model

Ground truth validation

Data collection

Feature extraction and modeling

Model evaluation

Page 39: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Data collection

• From SNAP dataset we extracted:

– Tweets in English

– Each has an embedded URI pointing to an external resource.

– The embedded URI is shortened via Bit.ly

– The external resource:

• Still persists.

• Has at least 10 mementos.

• Is unique.

We extracted 5,937 unique instances

Hany SalahEldeen & Michael Nelson 35 Reading the Correct History?

Page 40: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Get the closest memento

Hany SalahEldeen & Michael Nelson 35 Reading the Correct History?

… t1 t2

tn

t4 t3

Δ1 Δ2 < Pick Memento @ t1

Page 41: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Sorted Time Delta between tweet and closest memento

Hany SalahEldeen & Michael Nelson 36 Reading the Correct History?

Randomly selected 1,124 instances Time delta range: 3.07 minutes to 56.04 hours Average: 25.79 hours ~ 1 day

Tweet time

After Tweet time

Before Tweet time

Page 42: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Training dataset

• Rcurrent: The state of the resource at current time.

• Rclick: The state of the resource at click time.

Hany SalahEldeen & Michael Nelson 37 Reading the Correct History?

Relevant Assignments 929 82.65%

Non-Relevant Assignments 195 17.35%

5 MT workers agreeing (5-0 split) 589 52.40%

4 MT workers agreeing (4-1 split) 309 27.49%

3 MT workers agreeing (3-2 close call split) 226 20.11%

Page 43: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

The game plan

Hany SalahEldeen & Michael Nelson 38 Reading the Correct History?

Problem Illustration

Training data collection attempts

The TIRM model

Ground truth validation

Data collection

Feature extraction and modeling

Model evaluation

Page 44: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Feature extraction

• For each tweet we perform:

– Link analysis

– Social Media Mining

– Archival Existence

– Sentiment Analysis

– Content Similarity

– Entity Identification

Hany SalahEldeen & Michael Nelson 39 Reading the Correct History?

Page 45: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Link analysis

• Since the tweets have embedded resources shortened by Bit.ly we can extract: – Total number of clicks

– Hourly click logs

– Creation dates

– Referring websites

– Referring countries.

• We calculate the depth of the resource in relation to its domain (either it is a leaf node or a root page) – We calculated the number of backslashes in the resource’s URI

Hany SalahEldeen & Michael Nelson 40 Reading the Correct History?

Page 46: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Social Media Mining

• Twitter:

– Using Topsy.com’s API to extract: • Total number of tweets.

• The most recent 500.

• Number of tweets by influential users.

Hany SalahEldeen & Michael Nelson 41 Reading the Correct History?

The collection of tweets extracted provided an extended context of the resource authored by users in the twittersphere.

Page 47: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Social Media Mining

• Facebook:

– Mined too for likes, shares, posts, and clicks related to each resource.

Hany SalahEldeen & Michael Nelson 42 Reading the Correct History?

Page 48: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Archival Existence

• Using Memento Time Maps we get: – Total mementos

available

– Different archives count.

– The closest archived version to the tweet time.

Hany SalahEldeen & Michael Nelson 43 Reading the Correct History?

Page 49: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Sentiment Analysis • Using NLTK libraries of natural language text processing

• Extract the most prominent sentiment in the text

Hany SalahEldeen & Michael Nelson 44 Reading the Correct History?

Page 50: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Content Similarity • Steps:

– We download the content HTML using Lynx browser.

– We apply boilerplate removal algorithm and full text extraction.

– Calculate the cosine similarity between the two pages.

Hany SalahEldeen & Michael Nelson 45 Reading the Correct History?

70% similarity

Page 51: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Entity Identification • By visual inspection we observed that the majority of tweets about

celebrities are related to current events.

• We harvested Wikipedia for lists of actors, politicians, and athletes.

• Checked the existence of a celebrity mention in the tweets.

Hany SalahEldeen & Michael Nelson 46 Reading the Correct History?

Actor: Johnny Depp

Page 52: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

• To remove confusion we removed the close calls

898 instances remaining

Relevant Assignments 929 82.65%

Non-Relevant Assignments 195 17.35%

5 MT workers agreeing (5-0 split) 589 52.40%

4 MT workers agreeing (4-1 split) 309 27.49%

3 MT workers agreeing (3-2 close call split) 226 20.11%

Modeling and Classification

Hany SalahEldeen & Michael Nelson 47 Reading the Correct History?

Page 53: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

The trained classifier

• From the feature extraction phase we extracted 39 different features to train the classifier.

• Using 10-fold cross validation, the Cost Sensitive Classifier Based on Random Forests gave the highest success rate = 90.32%

Hany SalahEldeen & Michael Nelson 48 Reading the Correct History?

Page 54: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Testing the model

Hany SalahEldeen & Michael Nelson 49 Reading the Correct History?

10-Fold Cross-Validation Testing

Classifier Mean Absolute Error

Root Mean Squared Error

Kappa Statistic

Incorrectly Classified %

Correctly Classified %

Cost sensitive classifier based on Random Forest

0.15 0.27 0.39 9.68% 90.32%

Classifier Precision Recall F-measure Class

Cost sensitive classifier based on Random Forest

0.93 0.53

0.96 0.37

0.95 0.44

Relevant Non-Relevant

Weighted Average 0.89 0.90 0.90

Page 55: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Feature significance

• Since we have 39 features, we needed to understand the effect of each feature and which are the strongest ones affecting the classification

• We applied an attribute evaluator supervised algorithm based on Ranker search to find the strongest features

Hany SalahEldeen & Michael Nelson 50 Reading the Correct History?

Page 56: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Most significant features sorted by information gain

Hany SalahEldeen & Michael Nelson 51 Reading the Correct History?

Rank Feature Gain Ratio

1 Existence of celebrities in tweets 0.149

2 Number of mementos 0.090

3 Tweet similarity with current page 0.071

4 Similarity: Current & past page 0.0527

5 Similarity: Tweet & past page 0.04401

6 Original URI’s depth 0.0324

Page 57: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

The game plan

Hany SalahEldeen & Michael Nelson Reading the Correct History?

Problem Illustration

Training data collection attempts

The TIRM model

Ground truth validation

Data collection

Feature extraction and modeling

Model evaluation

Page 58: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Model Evaluation

• Next step was to test the trained model against other datasets and examine the results.

• We tested against: – The remaining 4,813 from the original 5,937 instances after extracting the

1,124 used in training.

– The Tweet Collections based on historic events. (MJ, Obama, Iran, Syria, & H1N1)

Hany SalahEldeen & Michael Nelson 52 Reading the Correct History?

Page 59: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Results of testing the model against multiple datasets

Hany SalahEldeen & Michael Nelson 53 Reading the Correct History?

Dataset Status 200 Status 404 of other Relevant % Non-Relevant %

Extended 4,813 instances 96.77% 3.23% 96.74% 3.26%

MJ’s Death 57.54% 42.46% 93.24% 6.76%

H1N1 Outbreak 8.96% 91.04% 97.48% 2.52%

Iran Elections 68.21% 31.79% 94.69% 5.31%

Obama’s Nobel Prize 62.86% 37.14% 93.89% 6.11%

Syrian Uprising 80.80% 19.20% 70.26% 29.75%

Page 60: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Hany SalahEldeen & Michael Nelson 54 Reading the Correct History?

Idea: We need to transform the problem from intention to

relevance.

Recap…

Now we need to transform it back!

Page 61: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Mapping TIRM

• We used 70% similarity as a threshold of relevancy.

Hany SalahEldeen & Michael Nelson 55 Reading the Correct History?

Page 62: Reading the Correct History? Modeling Temporal Intention in Resource Sharing

Conclusions • TIRM successfully transfers the temporal intention

problem to a temporal relevancy problem.

• Temporal relevancy is easier to solve and MT workers provide almost perfect agreement with experts’ opinions.

• We successfully collected a gold standard dataset of temporal user intention.

• We found a temporal inconsistency in the shared resource ranging from <1% to 25% according to the dataset.

Hany SalahEldeen & Michael Nelson 56 Reading the Correct History?