Connotation Lexicon: A Dash of Sentiment Beneath the Surface Meaning Understanding the connotation of words plays an important role in interpreting subtle shades of sentiment beyond denotative or surface meaning of text, as seemingly objective statements often allude nuanced sentiment of the writer, and even purposefully conjure emotion from the readers’ minds. The focus of our work is drawing nuanced, connotative sentiments from even those words that are objective on the surface, such as “intelligence”, “human”, and “cheesecake”. We developed induction algorithms encoding a diverse set of linguistic insights (semantic prosody, distributional similarity, semantic parallelism of coordination) and prior knowledge drawn from lexical resources, resulting in the first broad-coverage connotation lexicon.

Online Search

Examples

	Positive	Negative	Neutral
Nouns	avatar, adrenaline, keynote, debut, stakeholder, sunshine, cooperation	unbeliever, delay, shortfall, gunshot, misdemeanor, mutiny, rigor	header, heat, mark, clothing, outline, grid, gasoline, course, preview
Verbs	handcraft, accredit, volunteer, party,personalize, nurse, google	sentence, cough, trap, scratch, debunk, rip, misspell, overcharge	state, edit, send, put, arrive, type, drill, name, stay, echo, register
Adjectives	floral, vegetarian, prepared, ageless, funded, contemporary, detailed	debilitating, impaired, swollen, intentional, jarring, unearned	same, cerebral, west, hydrated, routine, uncut, automatic, unheated

Relevant Papers

Learning General Connotation of Words using Graph-based Algorithms. Song Feng, Ritwik Bose, and Yejin Choi. Empirical Methods in Natural Language Processing (EMNLP) , 2011. [pdf]

Citation: please cite the following if using our connotation lexicon.

	@InProceedings{feng:2013:ACL2013,
	author    = {Feng, Song  and  Kang, Jun Sak and Kuznetsova, Polina  and  Choi, Yejin},
	title     = {Connotation Lexicon: A Dash of Sentiment Beneath the Surface Meaning},
	booktitle = {Proceedings of the 51th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
	month     = {Angust},
	year      = {2013},
	address   = {Sofia, Bulgaria},
	publisher = {Association for Computational Linguistics},
	}
			

Download

Lexicon	Description
Version-May2013	Stats: Total: 93,873 Nouns (n.): 45,185 Proper Nouns (pn.): 21,983 Adjectives (a.): 18,800 Verbs (v.): 7,905 Algorithm: Constraint optimization based on linear programming. Connotative Predicates: 20 Positive Predicates, 20 Negative Predicates