SemEval-2007 Task 14: Affective Text

By Carlo Strapparava, Rada Mihalcea. International Workshop on Semantic Evaluation, 2007

885 citations recorded by the source corpus.

The "Affective Text" task focuses on the classification of emotions and valence (positive/negative polarity) in news headlines, and is meant as an exploration of the connection between emotions and lexical semantics. In this paper, we describe the data set used in the evaluation and the results obtained by the participating systems.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/a5fca08fe28f909dd0a9c0821ca5cb51c9d6fe39

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

EmoBank: Studying the Impact of Annotation Perspective and Representation Format on Dimensional Emotion Analysis (2017, methodology): “This includes the extension from only two to multiple polarity classes or even real-valued scores (Strapparava and Mihalcea, 2007), the aggregation of multiple aspects of an opinion item into a composite opinion statement for the whole item (Schouten and Frasincar, 2016), and sentiment…”
Harnessing Twitter "Big Data" for Automatic Emotion Identification (2012, background): “In this paper, we focus on supervised emotion identification literature and how to automatically collect training data rather than rule-based approaches [10], [15].”
Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset (2018, background): “This dataset is larger and contains a more extensive set of emotions than many similar emotion prediction datasets from other text domains such as Scherer and Wallbott (1994), Strapparava and Mihalcea (2007), Mo-hammad et al. (2018), and Gupta et al. (2017).”
Multimodal sentiment analysis: A systematic review of history, datasets, multimodal fusion methods, applications, challenges and future directions (2022, background): “The idea of detecting emotion in news headlines was discussed by a group of researchers [4].”
Finnish resources for evaluating language model semantics (2017, background): “67, it can be considered suf-ﬁciently high as inter-annotator agreements can be relatively low in similar ambiguous tasks (Ga-mon, 2004; Strapparava and Mihalcea, 2007).”
Current State of Text Sentiment Analysis from Opinion to Emotion Mining (2017, background): “Strapparava and Mihalcea [2007] developed a dataset for the SemEval 2007 workshop on the shared task of affective computing.”
Sentiment Analysis: Detecting Valence, Emotions, and Other Affectual States from Text (2016, background): “Alm, Roth, and Sproat (2005) annotated 22 Grimm fairy tales (1580 sentences) for Ekman emotions.15 Strapparava and Mihalcea (2007) annotated newspaper headlines with intensity scores for each of the Ekman emotions, referred to as the Text Affect Dataset.16 Aman and Szpakowicz (2007) annotated blog…”
Modeling Empathy and Distress in Reaction to News Stories (2018, background): “Yet such approaches, often rooted in psychological theory, also turned out to be more challenging in respect to annotation and modeling (Strapparava and Mihalcea, 2007).”
Lexicon-Based Methods for Sentiment Analysis (2011, background): “The Affective Text data from Rada Mihalcea and Carlo Strappavara was used in the 2007 SemEval task.”
EmoNet: Fine-Grained Emotion Detection with Gated Recurrent Neural Networks (2017, methodology): “Our work differs from both that of SEM07 (Strapparava and Mihalcea, 2007) and (Aman and Szpakowicz, 2007) in that we focus on a different genre (i.e., Twitter) and investigate distant supervision as a way to acquire a signiﬁcantly larger labeled dataset.”
Dataless Knowledge Fusion by Merging Weights of Language Models (2022, positive): “We use Emoint (Moham-mad & Bravo-Marquez, 2017), SSEC (Schuff et al., 2017), ElectoralTweets (Mohammad et al., 2015), GroundedEmotions (Liu et al., 2017), and AffectiveText (Strapparava & Mihalcea, 2007) as held-out datasets for evaluating out-of-domain generalization.”
Cheap and Fast – But is it Good? Evaluating Non-Expert Annotations for Natural Language Tasks (2008, methodology): “This experiment is based on the affective text annotation task proposed in Strapparava and Mihalcea (2007), wherein each annotator is presented with a list of short headlines, and is asked to give numeric judgments in the interval [0,100] rating the headline for six emotions: anger, disgust, fear,…”
Towards multimodal sentiment analysis: harvesting opinions from the web (2011, methodology): “Another manually annotated corpus is the collection of newspaper headlines created and used during the Semeval task on “Affective Text” [25], which consists of 1000 test headlines and 200 development headlines, each of them annotated with”
#Emotional Tweets (2012, methodology): “The SemEval-2007 Affective Text corpus has newspaper headlines labeled with the six Ekman emotions by six annotators (Strapparava and Mihalcea, 2007).”