acl acl2013 acl2013-79 knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Eric T. Nalisnick ; Henry S. Baird
Abstract: We present an automatic method for analyzing sentiment dynamics between characters in plays. This literary format’s structured dialogue allows us to make assumptions about who is participating in a conversation. Once we have an idea of who a character is speaking to, the sentiment in his or her speech can be attributed accordingly, allowing us to generate lists of a character’s enemies and allies as well as pinpoint scenes critical to a character’s emotional development. Results of experiments on Shakespeare’s plays are presented along with discussion of how this work can be extended to unstructured texts (i.e. novels).
Reference: text
sentIndex sentText sentNum sentScore
1 of Computer Science and Engineering Lehigh University Bethlehem, PA 18015, USA {etn2 12 ,hsb2 } @ lehigh . [sent-4, score-0.051]
2 edu Abstract We present an automatic method for analyzing sentiment dynamics between characters in plays. [sent-5, score-0.495]
3 This literary format’s structured dialogue allows us to make assumptions about who is participating in a conversation. [sent-6, score-0.14]
4 Once we have an idea of who a character is speaking to, the sentiment in his or her speech can be attributed accordingly, allowing us to generate lists of a character’s enemies and allies as well as pinpoint scenes critical to a character’s emotional development. [sent-7, score-0.6]
5 Results of experiments on Shakespeare’s plays are presented along with discussion of how this work can be extended to unstructured texts (i. [sent-8, score-0.117]
6 1 Introduction Insightful analysis of literary fiction often challenges trained human readers let alone machines. [sent-11, score-0.222]
7 In fact, some humanists believe literary analysis is so closely tied to the human condition that it is impossible for computers to perform. [sent-12, score-0.169]
8 In his book Reading Machines: Toward an Algorithmic Criticism, Stephen Ramsay (201 1) states: Tools that can adjudicate the hermeneutical parameters of human reading experiences. [sent-13, score-0.042]
9 Antonio Roque (2012) has challenged Ramsay’s claim, and certainly there has been successful work done in the computational analysis and modeling of narratives, as we will review in the next section. [sent-17, score-0.029]
10 However, we believe that most previous work (except possibly (Elsner, 2012)) has failed to directly address the root cause of Ramsay’s skepticism: can computers extract the emotions encoded in a narrative? [sent-18, score-0.119]
11 For example, can the love that Shakespeare’s Juliet feels for Romeo be computationally tracked? [sent-19, score-0.044]
12 Empathizing with characters along their journeys to emotional highs and lows is often what makes a narrative compelling for a reader, and therefore we believe mapping these journeys is the first step in capturing the human reading experience. [sent-20, score-0.464]
13 Unfortunately but unsurprisingly, computational modeling of the emotional relationships described in natural language text remains a daunting technical challenge. [sent-21, score-0.154]
14 The reason this task is so difficult is that emotions are indistinct and often subtly conveyed, especially in text with literary merit. [sent-22, score-0.193]
15 Humans typically achieve no greater than 80% accuracy in sentiment classification experiments involving product reviews (Pang et al. [sent-23, score-0.389]
16 Similar experiments on fiction texts would presumably yield even higher error rates. [sent-25, score-0.086]
17 In order to attack this open problem and make further progress towards refuting Ramsay’s claim, we turn to shallow statistical approaches. [sent-26, score-0.039]
18 In the following paper, we describe our attempts to use modern sentiment lexicons and dialogue structure to algorithmically track and model–with no domain-specific customization–the emotion dynamics between characters in Shakespeare’s plays. [sent-28, score-0.68]
19 1 2 Sentiment Analysis and Related Work Sentiment analysis (SA) is now widely used commercially to infer user opinions from product reviews and social-media messages (Pang and Lee, 1XML versions provided by Jon http://www. [sent-29, score-0.058]
20 IMDB’s user reviews are labeled with one to ten stars, which are assumed to correlate with the text’s polarity) (Pang et al. [sent-36, score-0.029]
21 These methods are driven by sentiment lexicons, fixed lists associating words with “valences” (signed integers representing positive and negative feelings) (Kim and Hovy, 2004). [sent-40, score-0.454]
22 Some lexicons allow for analysis of specific emotions by associating words with degrees of fear, joy, surprise, anger, anticipation, etc. [sent-41, score-0.186]
23 Turning our attention now to automatic semantic analysis of fiction, it seems that narrative modeling and summarization has been the most intensively studied application. [sent-44, score-0.16]
24 Narrative structure has also been studied by representing character interactions as networks. [sent-46, score-0.059]
25 Mutton (2004) adapted methods for extracting social networks from Internet Relay Chat (IRC) to mine Shakespeare’s plays for their networks. [sent-47, score-0.161]
26 Extending this line of work to novels, Elson and McKeown (2010) developed a reliable method for speech attribution in unstructured texts, and then used this method to successfully extract social networks from Victorian novels (Elson et al. [sent-48, score-0.38]
27 While structure is undeniably important, we believe analyzing a narrative’s emotions is essential to capturing the ‘reading experience,’ which is a view others have held. [sent-51, score-0.146]
28 Alm and Sproat (2005) analyzed Brothers Grimm fairy tales for their ‘emotional trajectories,’ finding emotion typically increases as a story progresses. [sent-52, score-0.215]
29 Mohammad (201 1) scaled-up their work by using a crowdsourced emotion lexicon to track emotion dynam- ics over the course of many novels and plays, including Shakespeare’s. [sent-53, score-0.432]
30 In the most recent work we are aware of, Elsner (2012) analyzed emotional trajectories at the character level, showing how Miss Elizabeth Bennet’s emotions change over the course of Pride and Prejudice. [sent-54, score-0.383]
31 3 Character-to-Character Sentiment Analysis Figure 1: The characters in Hamlet are ranked by Hamet’s sentiment towards them. [sent-55, score-0.457]
32 We attempt to further Elsner’s line of work by leveraging text structure (as Mutton and Elson did) and knowlege-based SA to track the emotional trajectories of interpersonal relationships rather than of a whole text or an isolated character. [sent-57, score-0.356]
33 This assumption doesn’t always hold; it is not uncommon to find a scene in which two characters are expressing feelings about someone offstage. [sent-59, score-0.33]
34 Yet our initial results on Shakespeare’s plays show that the instances of face-to-face dialogue produce a strong enough signal to generate sentiment rankings that match our expectations. [sent-60, score-0.502]
35 For example, Hamlet’s sentiment rankings upon the conclusion of his play are shown in Figure 1. [sent-61, score-0.448]
36 Not surprisingly, Claudius draws the most negative sentiment from Hamlet, receiving a score of -27. [sent-62, score-0.422]
37 On the other hand, Gertrude is very well liked by Hamlet (+24), which is unexpected (at least to 480 us) since Hamlet suspects that his mother was involved in murdering King Hamlet. [sent-63, score-0.073]
38 Figure 2: The above chart tracks how Gertrude’s and Hamlet’s sentiment towards one another changes over the course of the play. [sent-64, score-0.442]
39 Hamlet’s sen- timent for Gertrude is denoted by the black line, and Gertrude’s for Hamlet is marked by the opposite boundary of the dark/light gray area. [sent-65, score-0.277]
40 1 Peering into the Queen’s Closet To gain more insight into this mother-son relationship, we examined how their feelings towards one another change over the course of the play. [sent-68, score-0.2]
41 Figure 2 shows the results of dynamic characterto-character sentiment analysis on Gertrude and Hamlet. [sent-69, score-0.389]
42 The running total of Hamlet’s sentiment valence toward Gertrude is tracked by the black line, and Gertrude’s feelings toward her son are tracked by the opposite boundary of the light/dark gray area. [sent-70, score-1.027]
43 The line graph shows a dramatic swing in sentiment around line 2,250, which corresponds to Act iii, Scene iv. [sent-71, score-0.474]
44 In this scene, entitled The Queen ’s Closet, Hamlet confronts his mother about her involvement in King Hamlet’s death. [sent-72, score-0.11]
45 Gertrude is shocked at the accusation, revealing she never suspected Ham- let’s father was murdered. [sent-73, score-0.03]
46 King Hamlet’s ghost even points this out to his son: “But, look, amazement on thy mother sits” (3. [sent-74, score-0.118]
47 Hamlet then comes to the realization that his mother had no involvement in the murder and probably married Claudius more so to preserve stability in the state. [sent-77, score-0.152]
48 As a result, Hamlet’s affection towards his mother grows, as exhibited in the sentiment jump from -1 to 22. [sent-78, score-0.499]
49 But this scene has the opposite affect on Gertrude: she sees her son murder an innocent man (Polonius) and talk to an invisible presence (she cannot see King Hamlet’s ghost). [sent-79, score-0.27]
50 Because of Gertrude’s realization, it is only natural that her sentiment undergoes a sharply negative change (1to -19). [sent-81, score-0.394]
51 2 Analyzing Shakespeare’s Most Famous Couples Figure 3: Othello’s sentiment for Desdemona is denoted by the black line, and Desdemona’s for Othello is marked by the opposite boundary of the dark/light gray area. [sent-83, score-0.637]
52 As expected, the line graph shows Othello has very strong positive emotion towards his new wife at the beginning of the play, but this positivity quickly degrades as Othello falls deeper and deeper into Iago’s deceit. [sent-84, score-0.27]
53 After running this automatic analysis on all of Shakespeare’s plays, not all the results examined were as enlightening as the Hamlet vs. [sent-85, score-0.029]
54 We clearly see Othello’s love for his new bride climaxes in the first third of the play and then rapidly degrades due to Iago’s deceit while Desdemona’s feelings for Othello stay positive until the very end of the play when it is clear Othello’s love for her has become poisoned. [sent-91, score-0.465]
55 As expected, the two exhibit rapidly increasing positive sentiment for each other that only tapers when the play takes a tragic course in the latter half. [sent-94, score-0.522]
56 The phases of Petruchio’s courtship can be seen: first he is neutral to her, then ‘tames’ her with a 481 period of negative sentiment, and finally she embraces him, as shown by the increasingly positive sentiment exhibited in both directions. [sent-97, score-0.45]
57 Figure 4: Juliet’s sentiment for Romeo is denoted by the black line, and Romeo’s for Juliet is marked by the opposite boundary of the gray area. [sent-98, score-0.637]
58 Aligning with our expectations, both characters exhibit strong positive sentiment towards the other throughout the play. [sent-99, score-0.486]
59 Unfortunately, we do not have room in this paper to discuss further examples, but a visualization of sentiment dynamics between any pair of characters in any of Shakespeare’s plays can be seen at www. [sent-100, score-0.551]
60 Figure 5: Petruchio’s sentiment for Katharina is denoted by the black line, and Katharina’s for Petruchio is marked by the opposite boundary of the dark/light gray area. [sent-104, score-0.637]
61 The period from line 1200 to line 1700, during which Petruchio exhibits negative sentiment, marks where he is ‘taming’ the ‘shrew. [sent-105, score-0.148]
62 ’ 4 Future Work While this paper presents experiments on just Shakespeare’s plays, note that the described technique can be extended to any work of fiction writ- ten since the Elizabethan Period. [sent-106, score-0.086]
63 The sentiment lexicon we used, AFINN, is designed for modern English; thus, it should only provide better analysis on works written after Shakespeare’s. [sent-107, score-0.389]
64 Furthermore, character-to-character analysis should be able to be applied to novels (and other unstructured fiction) if Elson and McKeown’s (2010) speaker attribution technique is first run on the work. [sent-108, score-0.278]
65 Not only can these techniques be extended to novels but also be made more precise. [sent-109, score-0.138]
66 For instance, the assumption that the current speaker’s sentiment is directed toward the previous speaker is rather naive. [sent-110, score-0.436]
67 A speech could be analyzed for context clues that signal that the character speaking is not talking about someone present but about someone out of the scene. [sent-111, score-0.193]
68 The sentiment could then be redirected to the not-present character. [sent-112, score-0.36]
69 Furthermore, detecting subtle rhetorical features such as irony and deceit would markedly improve the accuracy ofthe analysis on some plays. [sent-113, score-0.074]
70 For example, our character-to-character analysis fails to detect that Iago hates Othello because Iago gives his commander constant lip service in order to manipulate him–only revealing his true feelings at the play’s conclusion. [sent-114, score-0.177]
71 5 Conclusions As demonstrated, shallow, un-customized sentiment analysis can be used in conjunction with text structure to analyze interpersonal relationships described within a play and output an interpretation that matches reader expectations. [sent-115, score-0.554]
72 This character-to-character sentiment analysis can be done statically as well as dynamically to possibly pinpoint influential moments in the narrative (which is how we noticed the importance of Hamlet’s Act 3, Scene 4 to the Hamlet-Gertrude relationship). [sent-116, score-0.565]
73 Clac and clac-nb: knowledge-based and corpus-based approaches to sentiment tagging. [sent-133, score-0.36]
74 From once upon a time to happily ever after: Tracking emotions in novels and fairy tales. [sent-184, score-0.301]
75 Inferring and visualizing social networks on internet relay chat. [sent-190, score-0.129]
wordName wordTfidf (topN-words)
[('hamlet', 0.376), ('sentiment', 0.36), ('shakespeare', 0.333), ('gertrude', 0.307), ('othello', 0.231), ('elson', 0.181), ('novels', 0.138), ('narrative', 0.131), ('petruchio', 0.128), ('feelings', 0.118), ('scene', 0.113), ('emotion', 0.112), ('emotional', 0.11), ('literary', 0.107), ('desdemona', 0.102), ('iago', 0.102), ('ramsay', 0.102), ('romeo', 0.102), ('fiction', 0.086), ('emotions', 0.086), ('plays', 0.083), ('afinn', 0.077), ('claudius', 0.077), ('fairy', 0.077), ('juliet', 0.077), ('gray', 0.075), ('mother', 0.073), ('opposite', 0.068), ('pang', 0.065), ('katharina', 0.063), ('closet', 0.063), ('play', 0.062), ('character', 0.059), ('trajectories', 0.059), ('interpersonal', 0.059), ('tracked', 0.059), ('characters', 0.058), ('line', 0.057), ('boundary', 0.053), ('king', 0.053), ('black', 0.052), ('queen', 0.052), ('lehigh', 0.051), ('mutton', 0.051), ('relay', 0.051), ('dynamics', 0.05), ('elsner', 0.049), ('son', 0.047), ('attribution', 0.047), ('toward', 0.046), ('deceit', 0.045), ('andreevskaia', 0.045), ('ghost', 0.045), ('journeys', 0.045), ('pinpoint', 0.045), ('taming', 0.045), ('social', 0.045), ('valence', 0.044), ('love', 0.044), ('relationships', 0.044), ('course', 0.043), ('alm', 0.042), ('murder', 0.042), ('reading', 0.042), ('someone', 0.041), ('lexicons', 0.04), ('mohammad', 0.04), ('towards', 0.039), ('involvement', 0.037), ('unsurprisingly', 0.037), ('stroudsburg', 0.035), ('unstructured', 0.034), ('negative', 0.034), ('pa', 0.034), ('mckeown', 0.033), ('agarwal', 0.033), ('degrades', 0.033), ('dialogue', 0.033), ('networks', 0.033), ('believe', 0.033), ('antonio', 0.031), ('associating', 0.031), ('affective', 0.031), ('act', 0.03), ('revealing', 0.03), ('speaker', 0.03), ('marked', 0.029), ('strapparava', 0.029), ('positive', 0.029), ('analysis', 0.029), ('reviews', 0.029), ('algorithmic', 0.029), ('rapidly', 0.028), ('draws', 0.028), ('track', 0.027), ('exhibited', 0.027), ('analyzing', 0.027), ('analyzed', 0.026), ('rankings', 0.026), ('speech', 0.026)]
simIndex simValue paperId paperTitle
same-paper 1 1.0000007 79 acl-2013-Character-to-Character Sentiment Analysis in Shakespeare's Plays
Author: Eric T. Nalisnick ; Henry S. Baird
Abstract: We present an automatic method for analyzing sentiment dynamics between characters in plays. This literary format’s structured dialogue allows us to make assumptions about who is participating in a conversation. Once we have an idea of who a character is speaking to, the sentiment in his or her speech can be attributed accordingly, allowing us to generate lists of a character’s enemies and allies as well as pinpoint scenes critical to a character’s emotional development. Results of experiments on Shakespeare’s plays are presented along with discussion of how this work can be extended to unstructured texts (i.e. novels).
2 0.21489196 188 acl-2013-Identifying Sentiment Words Using an Optimization-based Model without Seed Words
Author: Hongliang Yu ; Zhi-Hong Deng ; Shiyingxue Li
Abstract: Sentiment Word Identification (SWI) is a basic technique in many sentiment analysis applications. Most existing researches exploit seed words, and lead to low robustness. In this paper, we propose a novel optimization-based model for SWI. Unlike previous approaches, our model exploits the sentiment labels of documents instead of seed words. Several experiments on real datasets show that WEED is effective and outperforms the state-of-the-art methods with seed words.
3 0.20759715 2 acl-2013-A Bayesian Model for Joint Unsupervised Induction of Sentiment, Aspect and Discourse Representations
Author: Angeliki Lazaridou ; Ivan Titov ; Caroline Sporleder
Abstract: We propose a joint model for unsupervised induction of sentiment, aspect and discourse information and show that by incorporating a notion of latent discourse relations in the model, we improve the prediction accuracy for aspect and sentiment polarity on the sub-sentential level. We deviate from the traditional view of discourse, as we induce types of discourse relations and associated discourse cues relevant to the considered opinion analysis task; consequently, the induced discourse relations play the role of opinion and aspect shifters. The quantitative analysis that we conducted indicated that the integration of a discourse model increased the prediction accuracy results with respect to the discourse-agnostic approach and the qualitative analysis suggests that the induced representations encode a meaningful discourse structure.
4 0.19344544 318 acl-2013-Sentiment Relevance
Author: Christian Scheible ; Hinrich Schutze
Abstract: A number of different notions, including subjectivity, have been proposed for distinguishing parts of documents that convey sentiment from those that do not. We propose a new concept, sentiment relevance, to make this distinction and argue that it better reflects the requirements of sentiment analysis systems. We demonstrate experimentally that sentiment relevance and subjectivity are related, but different. Since no large amount of labeled training data for our new notion of sentiment relevance is available, we investigate two semi-supervised methods for creating sentiment relevance classifiers: a distant supervision approach that leverages structured information about the domain of the reviews; and transfer learning on feature representations based on lexical taxonomies that enables knowledge transfer. We show that both methods learn sentiment relevance classifiers that perform well.
5 0.18896697 284 acl-2013-Probabilistic Sense Sentiment Similarity through Hidden Emotions
Author: Mitra Mohtarami ; Man Lan ; Chew Lim Tan
Abstract: Sentiment Similarity of word pairs reflects the distance between the words regarding their underlying sentiments. This paper aims to infer the sentiment similarity between word pairs with respect to their senses. To achieve this aim, we propose a probabilistic emotionbased approach that is built on a hidden emotional model. The model aims to predict a vector of basic human emotions for each sense of the words. The resultant emotional vectors are then employed to infer the sentiment similarity of word pairs. We apply the proposed approach to address two main NLP tasks, namely, Indirect yes/no Question Answer Pairs inference and Sentiment Orientation prediction. Extensive experiments demonstrate the effectiveness of the proposed approach.
6 0.18063366 379 acl-2013-Utterance-Level Multimodal Sentiment Analysis
8 0.1618927 115 acl-2013-Detecting Event-Related Links and Sentiments from Social Media Texts
9 0.15070085 211 acl-2013-LABR: A Large Scale Arabic Book Reviews Dataset
10 0.13843416 345 acl-2013-The Haves and the Have-Nots: Leveraging Unlabelled Corpora for Sentiment Analysis
11 0.13514873 209 acl-2013-Joint Modeling of News Readerâ•Žs and Comment Writerâ•Žs Emotions
12 0.12871401 282 acl-2013-Predicting and Eliciting Addressee's Emotion in Online Dialogue
13 0.12549859 147 acl-2013-Exploiting Topic based Twitter Sentiment for Stock Prediction
14 0.11763806 184 acl-2013-Identification of Speakers in Novels
15 0.11710606 131 acl-2013-Dual Training and Dual Prediction for Polarity Classification
16 0.095411025 168 acl-2013-Generating Recommendation Dialogs by Extracting Information from User Reviews
17 0.093738385 187 acl-2013-Identifying Opinion Subgroups in Arabic Online Discussions
18 0.090581849 91 acl-2013-Connotation Lexicon: A Dash of Sentiment Beneath the Surface Meaning
19 0.089216009 117 acl-2013-Detecting Turnarounds in Sentiment Analysis: Thwarting
20 0.088820502 121 acl-2013-Discovering User Interactions in Ideological Discussions
topicId topicWeight
[(0, 0.129), (1, 0.239), (2, -0.036), (3, 0.208), (4, -0.066), (5, -0.106), (6, 0.068), (7, 0.048), (8, 0.064), (9, 0.154), (10, 0.103), (11, -0.05), (12, -0.033), (13, -0.024), (14, -0.001), (15, 0.015), (16, 0.019), (17, 0.019), (18, 0.077), (19, 0.1), (20, -0.092), (21, -0.101), (22, 0.001), (23, 0.027), (24, -0.053), (25, 0.066), (26, 0.061), (27, -0.024), (28, 0.03), (29, 0.039), (30, 0.007), (31, 0.031), (32, -0.078), (33, -0.056), (34, 0.021), (35, -0.039), (36, -0.02), (37, 0.011), (38, -0.006), (39, -0.024), (40, 0.011), (41, 0.011), (42, 0.014), (43, -0.016), (44, 0.012), (45, -0.043), (46, 0.01), (47, -0.049), (48, -0.065), (49, -0.025)]
simIndex simValue paperId paperTitle
same-paper 1 0.96408045 79 acl-2013-Character-to-Character Sentiment Analysis in Shakespeare's Plays
Author: Eric T. Nalisnick ; Henry S. Baird
Abstract: We present an automatic method for analyzing sentiment dynamics between characters in plays. This literary format’s structured dialogue allows us to make assumptions about who is participating in a conversation. Once we have an idea of who a character is speaking to, the sentiment in his or her speech can be attributed accordingly, allowing us to generate lists of a character’s enemies and allies as well as pinpoint scenes critical to a character’s emotional development. Results of experiments on Shakespeare’s plays are presented along with discussion of how this work can be extended to unstructured texts (i.e. novels).
2 0.79313189 379 acl-2013-Utterance-Level Multimodal Sentiment Analysis
Author: Veronica Perez-Rosas ; Rada Mihalcea ; Louis-Philippe Morency
Abstract: During real-life interactions, people are naturally gesturing and modulating their voice to emphasize specific points or to express their emotions. With the recent growth of social websites such as YouTube, Facebook, and Amazon, video reviews are emerging as a new source of multimodal and natural opinions that has been left almost untapped by automatic opinion analysis techniques. This paper presents a method for multimodal sentiment classification, which can identify the sentiment expressed in utterance-level visual datastreams. Using a new multimodal dataset consisting of sentiment annotated utterances extracted from video reviews, we show that multimodal sentiment analysis can be effectively performed, and that the joint use of visual, acoustic, and linguistic modalities can lead to error rate reductions of up to 10.5% as compared to the best performing individual modality.
3 0.75389779 188 acl-2013-Identifying Sentiment Words Using an Optimization-based Model without Seed Words
Author: Hongliang Yu ; Zhi-Hong Deng ; Shiyingxue Li
Abstract: Sentiment Word Identification (SWI) is a basic technique in many sentiment analysis applications. Most existing researches exploit seed words, and lead to low robustness. In this paper, we propose a novel optimization-based model for SWI. Unlike previous approaches, our model exploits the sentiment labels of documents instead of seed words. Several experiments on real datasets show that WEED is effective and outperforms the state-of-the-art methods with seed words.
4 0.72495043 284 acl-2013-Probabilistic Sense Sentiment Similarity through Hidden Emotions
Author: Mitra Mohtarami ; Man Lan ; Chew Lim Tan
Abstract: Sentiment Similarity of word pairs reflects the distance between the words regarding their underlying sentiments. This paper aims to infer the sentiment similarity between word pairs with respect to their senses. To achieve this aim, we propose a probabilistic emotionbased approach that is built on a hidden emotional model. The model aims to predict a vector of basic human emotions for each sense of the words. The resultant emotional vectors are then employed to infer the sentiment similarity of word pairs. We apply the proposed approach to address two main NLP tasks, namely, Indirect yes/no Question Answer Pairs inference and Sentiment Orientation prediction. Extensive experiments demonstrate the effectiveness of the proposed approach.
5 0.71756172 318 acl-2013-Sentiment Relevance
Author: Christian Scheible ; Hinrich Schutze
Abstract: A number of different notions, including subjectivity, have been proposed for distinguishing parts of documents that convey sentiment from those that do not. We propose a new concept, sentiment relevance, to make this distinction and argue that it better reflects the requirements of sentiment analysis systems. We demonstrate experimentally that sentiment relevance and subjectivity are related, but different. Since no large amount of labeled training data for our new notion of sentiment relevance is available, we investigate two semi-supervised methods for creating sentiment relevance classifiers: a distant supervision approach that leverages structured information about the domain of the reviews; and transfer learning on feature representations based on lexical taxonomies that enables knowledge transfer. We show that both methods learn sentiment relevance classifiers that perform well.
6 0.68088835 117 acl-2013-Detecting Turnarounds in Sentiment Analysis: Thwarting
7 0.67407048 148 acl-2013-Exploring Sentiment in Social Media: Bootstrapping Subjectivity Clues from Multilingual Twitter Streams
8 0.64527082 211 acl-2013-LABR: A Large Scale Arabic Book Reviews Dataset
9 0.63735944 131 acl-2013-Dual Training and Dual Prediction for Polarity Classification
10 0.60605288 209 acl-2013-Joint Modeling of News Readerâ•Žs and Comment Writerâ•Žs Emotions
11 0.58280623 91 acl-2013-Connotation Lexicon: A Dash of Sentiment Beneath the Surface Meaning
12 0.57359809 278 acl-2013-Patient Experience in Online Support Forums: Modeling Interpersonal Interactions and Medication Use
13 0.55778402 2 acl-2013-A Bayesian Model for Joint Unsupervised Induction of Sentiment, Aspect and Discourse Representations
14 0.54623878 282 acl-2013-Predicting and Eliciting Addressee's Emotion in Online Dialogue
15 0.52328634 345 acl-2013-The Haves and the Have-Nots: Leveraging Unlabelled Corpora for Sentiment Analysis
16 0.52292025 115 acl-2013-Detecting Event-Related Links and Sentiments from Social Media Texts
17 0.45976377 49 acl-2013-An annotated corpus of quoted opinions in news articles
18 0.42951313 81 acl-2013-Co-Regression for Cross-Language Review Rating Prediction
19 0.42632869 168 acl-2013-Generating Recommendation Dialogs by Extracting Information from User Reviews
20 0.42175812 147 acl-2013-Exploiting Topic based Twitter Sentiment for Stock Prediction
topicId topicWeight
[(0, 0.056), (6, 0.016), (11, 0.038), (15, 0.026), (24, 0.105), (26, 0.066), (35, 0.062), (42, 0.024), (48, 0.033), (65, 0.302), (70, 0.05), (88, 0.048), (90, 0.032), (95, 0.043)]
simIndex simValue paperId paperTitle
same-paper 1 0.81453687 79 acl-2013-Character-to-Character Sentiment Analysis in Shakespeare's Plays
Author: Eric T. Nalisnick ; Henry S. Baird
Abstract: We present an automatic method for analyzing sentiment dynamics between characters in plays. This literary format’s structured dialogue allows us to make assumptions about who is participating in a conversation. Once we have an idea of who a character is speaking to, the sentiment in his or her speech can be attributed accordingly, allowing us to generate lists of a character’s enemies and allies as well as pinpoint scenes critical to a character’s emotional development. Results of experiments on Shakespeare’s plays are presented along with discussion of how this work can be extended to unstructured texts (i.e. novels).
2 0.65233481 331 acl-2013-Stop-probability estimates computed on a large corpus improve Unsupervised Dependency Parsing
Author: David Marecek ; Milan Straka
Abstract: Even though the quality of unsupervised dependency parsers grows, they often fail in recognition of very basic dependencies. In this paper, we exploit a prior knowledge of STOP-probabilities (whether a given word has any children in a given direction), which is obtained from a large raw corpus using the reducibility principle. By incorporating this knowledge into Dependency Model with Valence, we managed to considerably outperform the state-of-theart results in terms of average attachment score over 20 treebanks from CoNLL 2006 and 2007 shared tasks.
3 0.48157364 2 acl-2013-A Bayesian Model for Joint Unsupervised Induction of Sentiment, Aspect and Discourse Representations
Author: Angeliki Lazaridou ; Ivan Titov ; Caroline Sporleder
Abstract: We propose a joint model for unsupervised induction of sentiment, aspect and discourse information and show that by incorporating a notion of latent discourse relations in the model, we improve the prediction accuracy for aspect and sentiment polarity on the sub-sentential level. We deviate from the traditional view of discourse, as we induce types of discourse relations and associated discourse cues relevant to the considered opinion analysis task; consequently, the induced discourse relations play the role of opinion and aspect shifters. The quantitative analysis that we conducted indicated that the integration of a discourse model increased the prediction accuracy results with respect to the discourse-agnostic approach and the qualitative analysis suggests that the induced representations encode a meaningful discourse structure.
4 0.4706305 318 acl-2013-Sentiment Relevance
Author: Christian Scheible ; Hinrich Schutze
Abstract: A number of different notions, including subjectivity, have been proposed for distinguishing parts of documents that convey sentiment from those that do not. We propose a new concept, sentiment relevance, to make this distinction and argue that it better reflects the requirements of sentiment analysis systems. We demonstrate experimentally that sentiment relevance and subjectivity are related, but different. Since no large amount of labeled training data for our new notion of sentiment relevance is available, we investigate two semi-supervised methods for creating sentiment relevance classifiers: a distant supervision approach that leverages structured information about the domain of the reviews; and transfer learning on feature representations based on lexical taxonomies that enables knowledge transfer. We show that both methods learn sentiment relevance classifiers that perform well.
5 0.47024229 279 acl-2013-PhonMatrix: Visualizing co-occurrence constraints of sounds
Author: Thomas Mayer ; Christian Rohrdantz
Abstract: This paper describes the online tool PhonMatrix, which analyzes a word list with respect to the co-occurrence of sounds in a specified context within a word. The cooccurrence counts from the user-specified context are statistically analyzed according to a number of association measures that can be selected by the user. The statistical values then serve as the input for a matrix visualization where rows and columns represent the relevant sounds under investigation and the matrix cells indicate whether the respective ordered pair of sounds occurs more or less frequently than expected. The usefulness of the tool is demonstrated with three case studies that deal with vowel harmony and similar place avoidance patterns.
6 0.46655962 184 acl-2013-Identification of Speakers in Novels
7 0.46621096 72 acl-2013-Bridging Languages through Etymology: The case of cross language text categorization
8 0.46612209 373 acl-2013-Using Conceptual Class Attributes to Characterize Social Media Users
9 0.46573466 229 acl-2013-Leveraging Synthetic Discourse Data via Multi-task Learning for Implicit Discourse Relation Recognition
10 0.46202528 369 acl-2013-Unsupervised Consonant-Vowel Prediction over Hundreds of Languages
11 0.46023393 194 acl-2013-Improving Text Simplification Language Modeling Using Unsimplified Text Data
12 0.45950544 128 acl-2013-Does Korean defeat phonotactic word segmentation?
13 0.45867822 230 acl-2013-Lightly Supervised Learning of Procedural Dialog Systems
14 0.45858711 187 acl-2013-Identifying Opinion Subgroups in Arabic Online Discussions
15 0.4585416 183 acl-2013-ICARUS - An Extensible Graphical Search Tool for Dependency Treebanks
16 0.45825785 144 acl-2013-Explicit and Implicit Syntactic Features for Text Classification
17 0.45749795 85 acl-2013-Combining Intra- and Multi-sentential Rhetorical Parsing for Document-level Discourse Analysis
18 0.45698082 233 acl-2013-Linking Tweets to News: A Framework to Enrich Short Text Data in Social Media
19 0.45686454 169 acl-2013-Generating Synthetic Comparable Questions for News Articles
20 0.45629627 377 acl-2013-Using Supervised Bigram-based ILP for Extractive Summarization