#Emotional Tweets

By Saif M. Mohammad. International Workshop on Semantic Evaluation, 2012

463 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/8a57d0864d3be2ed5397140cc68a146cfd1e01d6

How researchers see this paper

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

Citations in the corpus

Harnessing Twitter "Big Data" for Automatic Emotion Identification (2012, background): “Mohammad [9] also collects emotion tweets via emotion hashtags.”
CARER: Contextualized Affect Representations for Emotion Recognition (2018, background): “In emotion recognition studies, Plutchik’s wheel of emotions (Plutchik, 2001) or Ekman’s six basic emotions (Ekman, 1992), are commonly adopted to de-ﬁne emotion categories (Mohammad, 2012; Sut-tles and Ide, 2013).”
Like It or Not (2016, methodology): “…the interest of many researchers who analyzed Twitter data for a variety of different tasks such as making predictions [Bollen et al. 2011], detecting users’ sentiment towards different topics [Go et al. 2009], detecting users’ emotions [Mohammad 2012], and detecting irony [Reyes et al. 2013].”
Dataless Knowledge Fusion by Merging Weights of Language Models (2022, unknown): “We use DailyDialogs (Li et al., 2017), CrowdFlower, TEC (Mohammad, 2012), Tales-Emotion (Alm et al., 2005), and ISEAR (Scherer & Wallbott, 1994) for training domain-specific models.”
Challenges in Sentiment Analysis (2017, unknown): “…& Mihalcea, 2007; Aman & Szpakowicz, 2007; Tokuhisa, Inui, & Matsumoto, 2008; Neviarouskaya, Prendinger, & Ishizuka, 2009; Bellegarda, 2010; Mohammad, 2012; Boucouvalas, 2002; Zhe & Boucou-valas, 2002; Holzman & Pottenger, 2003; Ma, Prendinger, & Ishizuka, 2005; Mohammad, 2012; John,…”
Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm (2017, methodology): “Prior work has used theories of emotion such as Ekman’s six basic emotions and Plutchik’s eight basic emotions (Mohammad, 2012; Suttles and Ide, 2013).”
Sentiment Analysis of Short Informal Texts (2014, methodology): “Mohammad (2012) developed a classi-ﬁer to detect emotions using tweets with emotion word hashtags (e.g., #anger , #surprise ) as labeled data.”
Stance and Sentiment in Tweets (2016, background): “In sentiment and emotion analysis, weakly labeled data can be accumulated by using sentiment clues provided by the authors of the text–clues like emoticons and hashtags [Go et al. 2009; Mohammad 2012].”
EmoNet: Fine-Grained Emotion Detection with Gated Recurrent Neural Networks (2017, methodology): “Since there is no such human-labeled dataset publicly available, we follow (Mohammad, 2012; Mintz et al., 2009; Purver and Battersby, 2012; Gonz´alez-Ib´anez et al., 2011; Wang et al., 2012) in adopting distant supervision : We collect tweets with emotion-carrying hashtags as a surrogate for…”
Overview of the 3rd Author Profiling Task at PAN 2015 (2015, background): “highlight the results from kiprov15 [29] for Spanish, who obtained the second position with large features set containing n-grams, POS tags, character flooding, average sentence length, Twitter-specific features such as hashtags, urls, mentions, re-tweets, and different dictionaries such as NRC Hash”
The spread of true and false news online (2018, background): “The second dataset contains a list of 32,389 Twitter hashtags and their weighted associations with the same emotions [33] [63].”
Current State of Text Sentiment Analysis from Opinion to Emotion Mining (2017, methodology): “Mohammad [2012] introduced his corpus, called the “Twitter Emotion Corpus” (TEC), collected from Twitter, that will be explained in Section 6.2 and, similarly to Roberts et al. [2012], built binary SVMs, one for each emotion, using unigrams and bigrams as features.”
NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweets (2013, unknown): “Mohammad (2012) showed that hashtagged emotion”
How Translation Alters Sentiment (2016, methodology): “Some early findings of this work were first presented in Salameh, Mohammad, and Kiritchenko (2015).”
I Know the Feeling: Learning to Converse with Empathy (2018, methodology): “To select this set of labels, we drew inspiration from previous datasets (Scherer & Wall-bott, 1994; Strapparava & Mihalcea, 2007; Skerry & Saxe, 2015; Li et al., 2017; Mohammad, 2012), consolidating the labels from each into a merged list.”
Taste and smell words form an affectively loaded and emotionally flexible part of the English lexicon (2016, unknown): “…operationalising “sensory modality” using a set of modality norms (van Dantzig, Cowell, Zeelenberg, & Pecher, 2011; Lynott & Connell, 2009, 2013) and operationalising “emotional valence” using valence norms (Warriner et al., 2013) and valence data from a corpus-driven approach (Mohammad, 2012).”
Obtaining Reliable Human Ratings of Valence, Arousal, and Dominance for 20,000 English Words (2018, background): “• About 1000 high-frequency content terms, including emoticons, from the Hashtag Emotion Corpus (HEC) (Mohammad, 2012).”
GoEmotions: A Dataset of Fine-Grained Emotions (2020, background): “…(Strapparava and Mihalcea, 2007), Crowd-Flower (CrowdFlower, 2016), Electoral Tweets (Mohammad et al., 2015), ISEAR (Scherer and Wallbott, 1994), the Twitter Emotion Corpus (TEC) (Mohammad, 2012), EmoInt (Mohammad et al., 2018) and the Stance Sentiment Emotion Corpus (SSEC) (Schuff et al., 2017).”
Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset (2018, methodology): “We consider 32 emotion labels, listed in Figure 3, which we chose by aggregating labels from several emotion prediction datasets (Scherer and Wallbott, 1994; Strapparava and Mihalcea, 2007; Skerry and Saxe, 2015; Li et al., 2017; Mohammad, 2012).”