Probabilistic Sense Sentiment Similarity through Hidden Emotions
Mohtarami, Mitra and Lan, Man and Tan, Chew Lim

Article Structure

Abstract

Sentiment Similarity of word pairs reflects the distance between the words regarding their underlying sentiments.

Introduction

Sentiment similarity reflects the distance between words based on their underlying sentiments.

Sentiment Similarity through Hidden Emotions

As we discussed above, semantic similarity measures are less effective to infer sentiment similarity between word pairs.

Hidden Emotional Model

Online review portals provide rating mechanisms (in terms of stars, e. g. 5— or 10—star rating) to al—

Predicting Sentiment Similarity

We utilize the approach proposed in (Mohtarami et al., 2013) to compute the sentiment similarity between two words.

Applications

We explain our approach in utilizing sentiment similarity between words to perform IQAP inference and SO prediction tasks respectively.

Evaluation and Results

6.1 Data and Settings

Analysis and Discussions

7.1 Number and Types of Emotions

Related Works

Sentiment similarity has not received enough attention to date.

Conclusion

We propose a probabilistic approach to infer the sentiment similarity between word senses with respect to automatically learned hidden emotions.

Topics

semantic similarity

Appears in 17 sentences as: Semantic similarity (1) semantic similarity (16)
In Probabilistic Sense Sentiment Similarity through Hidden Emotions
  1. Semantic similarity measures such as Latent Semantic Analysis (LSA) (Landauer et al., 1998) can effectively capture the similarity between semantically related words like "car" and "automobile", but they are less effective in relating words with similar sentiment orientation like "excellent" and "superior".
    Page 1, “Introduction”
  2. For example, the following relations show the semantic similarity between some sentiment words computed by LSA:
    Page 1, “Introduction”
  3. We show that our approach effectively outperforms the semantic similarity measures in two NLP tasks: Indirect yes/no Question Answer Pairs (IQAPs) Inference and Sentiment Orientation (S0) prediction that are described as follows:
    Page 1, “Introduction”
  4. Previous research utilized the semantic relations between words obtained from WordNet (Hassan and Radev, 2010) and semantic similarity measures (e.g.
    Page 1, “Introduction”
  5. As we discussed above, semantic similarity measures are less effective to infer sentiment similarity between word pairs.
    Page 2, “Sentiment Similarity through Hidden Emotions”
  6. For this purpose, we utilize the semantic similarity between each two words and create an enriched matrix.
    Page 4, “Hidden Emotional Model”
  7. To compute the semantic similarity between word senses, we utilize their synsets as follows:
    Page 4, “Hidden Emotional Model”
  8. Turney and Littman (2003) proposed a method in which the SO of a word is calculated based on its semantic similarity with seven positive words minus its similarity with seven negative words as shown in Figure 5.
    Page 5, “Applications”
  9. PMI extracts the semantic similarity between words using their co—occurrences.
    Page 6, “Evaluation and Results”
  10. The second row of Table 4 show the results of using a popular semantic similarity measure, PMI, as the sentiment similarity (SS) measure in Figure 4.
    Page 6, “Evaluation and Results”
  11. Most previous works employed semantic similarity of word pairs to address SO prediction and IQAP inference tasks.
    Page 9, “Related Works”

See all papers in Proc. ACL 2013 that mention semantic similarity.

See all papers in Proc. ACL that mention semantic similarity.

Back to top.

similarity measures

Appears in 12 sentences as: similarity measure (5) similarity measures (7)
In Probabilistic Sense Sentiment Similarity through Hidden Emotions
  1. Semantic similarity measures such as Latent Semantic Analysis (LSA) (Landauer et al., 1998) can effectively capture the similarity between semantically related words like "car" and "automobile", but they are less effective in relating words with similar sentiment orientation like "excellent" and "superior".
    Page 1, “Introduction”
  2. We show that our approach effectively outperforms the semantic similarity measures in two NLP tasks: Indirect yes/no Question Answer Pairs (IQAPs) Inference and Sentiment Orientation (S0) prediction that are described as follows:
    Page 1, “Introduction”
  3. Previous research utilized the semantic relations between words obtained from WordNet (Hassan and Radev, 2010) and semantic similarity measures (e.g.
    Page 1, “Introduction”
  4. As we discussed above, semantic similarity measures are less effective to infer sentiment similarity between word pairs.
    Page 2, “Sentiment Similarity through Hidden Emotions”
  5. To apply our PSSS on IQAPS inference task, we use it as the sentiment similarity measure in the algorithm explained in Figure 4.
    Page 6, “Evaluation and Results”
  6. The second row of Table 4 show the results of using a popular semantic similarity measure , PMI, as the sentiment similarity (SS) measure in Figure 4.
    Page 6, “Evaluation and Results”
  7. Table 4 shows the effectiveness of our sentiment similarity measure .
    Page 7, “Evaluation and Results”
  8. They also utilized Latent Semantic Analysis (LSA) (Landauer et al., 1998) as another semantic similarity measure .
    Page 9, “Related Works”
  9. However, both PM and LSA are semantic similarity measure .
    Page 9, “Related Works”
  10. (2012), we used two semantic similarity measures (PMI and LSA) for the IQAP inference task.
    Page 9, “Related Works”
  11. We showed that measuring the sentiment similarities between the adjectives in question and answer leads to higher performance as compared to semantic similarity measures .
    Page 9, “Related Works”

See all papers in Proc. ACL 2013 that mention similarity measures.

See all papers in Proc. ACL that mention similarity measures.

Back to top.

word pairs

Appears in 8 sentences as: word pairs (8)
In Probabilistic Sense Sentiment Similarity through Hidden Emotions
  1. Sentiment Similarity of word pairs reflects the distance between the words regarding their underlying sentiments.
    Page 1, “Abstract”
  2. This paper aims to infer the sentiment similarity between word pairs with respect to their senses.
    Page 1, “Abstract”
  3. The resultant emotional vectors are then employed to infer the sentiment similarity of word pairs .
    Page 1, “Abstract”
  4. In this paper, we show that sentiment similarity between word pairs can be effectively utilized to compute SO of words.
    Page 1, “Introduction”
  5. 0 We propose an effective approach to predict the sentiment similarity between word pairs through hidden emotions at the sense level,
    Page 1, “Introduction”
  6. As we discussed above, semantic similarity measures are less effective to infer sentiment similarity between word pairs .
    Page 2, “Sentiment Similarity through Hidden Emotions”
  7. For this purpose, we repeat the experiment for SO prediction by computing sentiment similarity of word pairs with and without using synonyms and antonyms.
    Page 8, “Analysis and Discussions”
  8. Most previous works employed semantic similarity of word pairs to address SO prediction and IQAP inference tasks.
    Page 9, “Related Works”

See all papers in Proc. ACL 2013 that mention word pairs.

See all papers in Proc. ACL that mention word pairs.

Back to top.

synsets

Appears in 6 sentences as: synset (2) Synsets (1) synsets (3)
In Probabilistic Sense Sentiment Similarity through Hidden Emotions
  1. To compute the semantic similarity between word senses, we utilize their synsets as follows:
    Page 4, “Hidden Emotional Model”
  2. where, syn(w) is the synset of w. Let count(w,~, wi) be the co—occurrence of the w,- and w], and let count(w_,~) be the total word count.
    Page 4, “Hidden Emotional Model”
  3. In addition, note that employing the synset of the words help to obtain different emotional vectors for each sense of a word.
    Page 4, “Hidden Emotional Model”
  4. 7.2 Effect of Synsets and Antonyms
    Page 8, “Analysis and Discussions”
  5. We show the important effect of synsets and antonyms in computing the sentiment similarity of words.
    Page 8, “Analysis and Discussions”
  6. This is indicates that the synsets of the words can improve the quality of the enriched matrix.
    Page 8, “Analysis and Discussions”

See all papers in Proc. ACL 2013 that mention synsets.

See all papers in Proc. ACL that mention synsets.

Back to top.

word senses

Appears in 5 sentences as: Word Sense (1) word senses (4)
In Probabilistic Sense Sentiment Similarity through Hidden Emotions
  1. For this purpose, we propose to model the hidden emotions of word senses .
    Page 1, “Introduction”
  2. Thus, we assume that the number and types of basic emotions are hidden and not predefined and propose a Probabilistic Sense Sentiment Similarity (PSSS) approach to extract the hidden emotions of word senses to infer their sentiment similarity.
    Page 2, “Sentiment Similarity through Hidden Emotions”
  3. To compute the semantic similarity between word senses , we utilize their synsets as follows:
    Page 4, “Hidden Emotional Model”
  4. Furthermore, we employ Word Sense Disambiguation (WSD) to disambiguate the adjectives in the question and its corresponding answer.
    Page 7, “Evaluation and Results”
  5. We propose a probabilistic approach to infer the sentiment similarity between word senses with respect to automatically learned hidden emotions.
    Page 9, “Conclusion”

See all papers in Proc. ACL 2013 that mention word senses.

See all papers in Proc. ACL that mention word senses.

Back to top.

F-Measure

Appears in 4 sentences as: F-Measure (4)
In Probabilistic Sense Sentiment Similarity through Hidden Emotions
  1. F-Measure (SO Prediction) Ch \l
    Page 7, “Analysis and Discussions”
  2. F-Measure (IQAPs Inference) 3:.
    Page 7, “Analysis and Discussions”
  3. F-Measure Ch m 0'!
    Page 8, “Analysis and Discussions”
  4. F-Measure H N U) .5 Ln 0 O O O O
    Page 9, “Related Works”

See all papers in Proc. ACL 2013 that mention F-Measure.

See all papers in Proc. ACL that mention F-Measure.

Back to top.

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