Connecting the
dots between
Research Team: Carla Abreu, Jorge Teixeira, Prof. Eugénio Oliveira Domain: News
Objective
"
… larger and larger amounts of news content is published every day.
With this much data, it is often easy to miss the big picture.
”
(Shahaf and Guestrin, 2010)
Objective: Automatically aggregate similar news and build news chains
(Shahaf and Guestrin, 2010): Connecting the Dots Between News Articles …
How to do this ?
Similarity Keywords Extraction
News group
News group / Keywords
Arch
Similarity
Aim:
Clustering Similar News Challenges:
What news data are important for the similarity process? How can we use that data ? Which methods can we use in this process ?How can we evaluate this process ?
Similarity
Filter:
Normalization:
● remove punctuation marks;
● remove patterns;
● remove stop-words (snowball); ● words stemming (ptstemmer)
Revista de imprensa: destaques de "O Jogo" Jornais do dia
Mourinho diz que os seus brasileiros jogaram muito bem. Quiseram embraçá-lo com os 6-2 da goleada sofrida por Portugal.
Revista de imprensa: destaques do "Jornal de Notícias” Jornais do dia
Governo pressiona direcções das escolas. Ministério pondera avaliar conselhos executivos pelo sistema do sector público.
Similarity
News comparation: Similarity: ● Title - ST*; ● Teaser ( S) - STe*; ● Content - SC*. Temporary Window ● T* Values between 0 and 1
Title
Teaser
Similarity
First Approach
Similar Tree (manual threshold assignment; empirical values)
Second Approach
Classification methods (provide by scikit-learn; automatic approach)
● Decision Tree;
● Support Vector Classifier (SVC)
● SVC Linear
● Random Forest
Similarity
Features 1. Title Similarity 2. Teaser Similarity 3. Content Similarity Variables: ● S = 0,2 ● T = 1 ● Algoritm - LevenstheinSimilarity
Dataset
3 millions of Portuguese news published between 2008 and 2013
Training Set
● Select 100 news of each day (between 23 Dec 2012 and 22 Jan 2013)
○ Annotate randomly 371 comparisons
Test Set
1. TS1: Select 501 distinct news from 19 Nov 2012 - Annotate randomly 5101 comparisons
2. TS2: Select 210 distinct news from 19 Nov 2012 - Annotate randomly 1047 comparisons
Similarity
Similarity
Experimental Setup
Precision (P) Recall(R)
Accuracy(A) F measure (F)
True Positives (TP): number of similar news correctly identify;
False Positives (FP): number of non similar news identified as similar; True Negatives (TN): number of non similar news correctly identify; False Negatives (FN): number of similar news identified as non similar.
P = ___ TP_____ TP + FP A = ___ TP_+ TN_ __ TP + TN + FP+ FN R = ___ TP_____ TP + FN F = 2 * ___P * R___ P + R
Similarity
Results and Analyses
P R A F DecisionTree 0,958 0,932 0,985 0,945 SVC 0,993 0,963 0,994 0,978 SVC Linear 0,991 0,963 0,994 0,977 RandomForest 0,987 0,960 0,993 0,974 Gaussian 0,701 0,964 0,956 0,812 Similar Tree 0,999 0,839 0,974 0,912
RandomForest: Random Behaviour
Gaussian: Worst Performance
SVCs results are better than Decision Tree in all metrics
SVCs have similar results
SVC: Better combination of evaluation metrics
News Group
News 2014 (3 April to 20 June)
Number of news: 186 366 Cluster number: 23 047
Average amount of news per cluster: ~ 3,7
March 2014, 10-15
Number of news: 16.747
Keywords extraction
Aim:
Extract relevant terms from text. Challenges:
Can any word be considered a keyword ? Can a news be described by a simple word ? a compound word ? or an entity ? How we can extract useful keywords from the news ?
Keywords extraction
Approach Explicit Keywords ○ Simple (uni-grams) ○ Compound (n-grams) Implicit Keywords Entities Governo Tribunal Constitucionalrebeldes busca competição
atentado à bomba avião da Malaysia Airlines fase de grupos Presidente
Keywords extraction
Explicit Keywords
Pos Tagger (Pablo Gamallo) [n-grams]
Normalization:
Remove Patterns
Stemmer [uni-grams]
Term frequency - Inverse document frequency (TF-IDF):
o(W, DOC): number of occurences of WORD in DOCUMENT; npalavras(DOC): number of words in DOCUMENT
Implicit Keywords
Normalization
Relation between words ( Ventura, Silva 2013)
Corr(A,B) is based on Pearson’s correlation coefficient; ||D|| is the number of documents of corpus D; di is the i-th document in D; size(di) is its number of words and f(A, di) the frequency of term A in di. Corr(A, B) ranges -1 (non correlation) to +1(strong correlation)
(Ventura, Silva 2013): Automatic Extraction of Explicit and Implicit Keywords to Build Document Descriptors
Keywords extraction
Entities
Find Entities
Keywords extraction
A idade média dos entrevistados era de 11 anos no início do estudo, sendo rapazes três quartos do total
Os jovens que jogam jogos de vídeo têm mais propensão para pensar e agir de forma agressiva, indica um estudo feito a mais de 3.000 estudantes em Singapura e hoje divulgado.
O estudo, publicado pela revista da American Medical Association e baseado em três anos de trabalho com 3.034 jovens, concluiu, com base nas respostas dos estudantes, que havia uma ligação entre o uso frequente de jogos de vídeo e as altas taxas de comportamentos e pensamentos agressivos.
Keywords extraction
Dataset
4789 news articles from January to December (2012)
Test set:
1. select one day from each month of 2012 2. select three hours of each day
3. extract keywords
4. select 10 news from each day
Keywords extraction
Experimental Setup Results Evaluation Explicit - Simple 0,732 Explicit - Compound 0,762 Implicit ~ 0 Entity 0,804PalavrasChaveRepresentativas Number of words that represents the news
PalavrasChaveAtribuídas Number of words attributed to news
News Group / Keywords
Arch
Aim:
Connect groups of news Challenges:
Arch
Approach (explicit simple keywords, entities and personalities)
Normalization
● lowercase
● explicit simple keywords - reduce words to their stem
Find Personalities
● From entities and explicit compound keywords using Verbetes.
Distance:
|ka| number of words in news group a; |kb| number of words in news group b;
Arch
Approach (explicit compound keywords)
Normalization
● lowercase
● remove stop-words
All words have the same weigth
Distance:
Arch
Goldstandard
1408 news (2012, January)
● 131 groups of news
Trainset:
5671 comparisons between groups of news
● 277 connections
● 5394 non connections
Testset:
300 comparisons between groups of news
● 26 connections
Arch
Experiences
1. 6 Experiences
Metrics to calculate distance(D1 and D2)
2. 11 Experiences
Constraints to comparisons - number of entities
- number of personalities
Arch
Experimental Setup
Precision (P) Recall(R)
True Positives (TP): number of connections correctly identify;
False Positives (FP): number of non connections identified as connections; True Negatives (TN): number of non connections correctly identify;
False Negatives (FN): number of connections identified as non connections. P = ___ TP_____
TP + FP
R = ___ TP_____ TP + FN
Arch
Results and Analyses
Experiences
1. Metrics:
a. Explicit simple keyword: D1 b. Personalities: D1
c. Entities: D2
2. Constrains:
a. Entities >= 3
b. Explicit simple keyword similarity >= 0,2
Best Result Gaussian
Precision 0,941