Subgroup Detection in Ideological Discussions
Abu-Jbara, Amjad and Dasigi, Pradeep and Diab, Mona and Radev, Dragomir

Article Structure

Abstract

The rapid and continuous growth of social networking sites has led to the emergence of many communities of communicating groups.

Introduction

Online forums discussing ideological and political topics are commonl.

Related Work

2.1 Sentiment Analysis

Approach

In this section, we describe a system that takes a discussion thread as input and outputs the subgroup membership of each discussant.

Evaluation

In this section, we present several levels of evaluation of our system.

Conclusions

In this paper, we presented an approach for subgroup detection in ideological discussions.

Topics

entity mentioned

Appears in 6 sentences as: entities mentioned (1) entity mentioned (5)
In Subgroup Detection in Ideological Discussions
  1. The target of attitude could be another discussant or an entity mentioned in the discussion.
    Page 1, “Introduction”
  2. tity recognition and noun phrase chunking to identify the entities mentioned in the discussion.
    Page 2, “Introduction”
  3. The attitude profile of a discussant contains an entry for every other discussant and an entry for every entity mentioned in the discission.
    Page 2, “Introduction”
  4. A target could be another discussant or an entity mentioned in the discussion.
    Page 5, “Approach”
  5. The target of opinion can also be an entity mentioned in the discussion.
    Page 5, “Approach”
  6. As stated above, a target could be another discussant or an entity mentioned in the discussion.
    Page 6, “Approach”

See all papers in Proc. ACL 2012 that mention entity mentioned.

See all papers in Proc. ACL that mention entity mentioned.

Back to top.

named entity

Appears in 5 sentences as: named entities (1) Named Entity (1) named entity (3)
In Subgroup Detection in Ideological Discussions
  1. In our work, we extract as targets frequent noun phrases and named entities that are used by two or more different discussants.
    Page 2, “Related Work”
  2. In addition to this shallow parsing method, we also use named entity recognition (NER) to identify more entities.
    Page 5, “Approach”
  3. We use the Stanford Named Entity Recognizer (Finkel et al., 2005) for this purpose.
    Page 5, “Approach”
  4. 7) We only use named entity recognition to identify entity targets; i.e.
    Page 9, “Evaluation”
  5. Although using both named entity recognition (NER) and noun phrase chunking achieves better results, it
    Page 9, “Evaluation”

See all papers in Proc. ACL 2012 that mention named entity.

See all papers in Proc. ACL that mention named entity.

Back to top.

NER

Appears in 5 sentences as: NER (5)
In Subgroup Detection in Ideological Discussions
  1. Table 3: Some of the entities identified using NER and NP Chunking in a discussion thread about the US 2012 elections
    Page 5, “Approach”
  2. In addition to this shallow parsing method, we also use named entity recognition ( NER ) to identify more entities.
    Page 5, “Approach”
  3. Now, both mentions of Obama will be recognized by the Stanford NER system and will be identified as one entity.
    Page 6, “Approach”
  4. Although using both named entity recognition ( NER ) and noun phrase chunking achieves better results, it
    Page 9, “Evaluation”
  5. can also be noted from the results that NER contributes more to the system performance.
    Page 9, “Evaluation”

See all papers in Proc. ACL 2012 that mention NER.

See all papers in Proc. ACL that mention NER.

Back to top.

sentiment analysis

Appears in 4 sentences as: Sentiment Analysis (1) sentiment analysis (3)
In Subgroup Detection in Ideological Discussions
  1. We use sentiment analysis techniques to identify opinion expressions.
    Page 1, “Introduction”
  2. 2.1 Sentiment Analysis
    Page 2, “Related Work”
  3. Our work is related to a huge body of work on sentiment analysis .
    Page 2, “Related Work”
  4. A very detailed survey that covers techniques and approaches in sentiment analysis and opinion mining could be found in (Pang and Lee, 2008).
    Page 2, “Related Work”

See all papers in Proc. ACL 2012 that mention sentiment analysis.

See all papers in Proc. ACL that mention sentiment analysis.

Back to top.

vector space

Appears in 4 sentences as: vector space (4)
In Subgroup Detection in Ideological Discussions
  1. We use clustering techniques to cluster the attitude vector space .
    Page 2, “Introduction”
  2. This suggests that clustering the attitude vector space will achieve the goal and split the discussants into subgroups according to their opinion.
    Page 7, “Approach”
  3. We collect all the text posted by each participant and create a tf-idf representations of the text in a high dimensional vector space .
    Page 8, “Evaluation”
  4. We then cluster the vector space to identify subgroups.
    Page 8, “Evaluation”

See all papers in Proc. ACL 2012 that mention vector space.

See all papers in Proc. ACL that mention vector space.

Back to top.

baseline systems

Appears in 3 sentences as: Baseline Systems (1) baseline systems (2)
In Subgroup Detection in Ideological Discussions
  1. First, we compare our system to baseline systems .
    Page 7, “Evaluation”
  2. 4.1 Comparison to Baseline Systems
    Page 8, “Evaluation”
  3. Table 5: Comparison to baseline systems
    Page 8, “Evaluation”

See all papers in Proc. ACL 2012 that mention baseline systems.

See all papers in Proc. ACL that mention baseline systems.

Back to top.

evaluation metrics

Appears in 3 sentences as: Evaluation Metrics (1) evaluation metrics (2)
In Subgroup Detection in Ideological Discussions
  1. Before describing the experiments and presenting the results, we first describe the evaluation metrics we use.
    Page 7, “Evaluation”
  2. 4.0.1 Evaluation Metrics
    Page 7, “Evaluation”
  3. We use two evaluation metrics to evaluate subgroups detection accuracy: Purity and Entropy.
    Page 7, “Evaluation”

See all papers in Proc. ACL 2012 that mention evaluation metrics.

See all papers in Proc. ACL that mention evaluation metrics.

Back to top.

PDF available from www.aclweb.org.
Send us an email