Although improvements have been made in the performance of sentiment analysis tools, the automatic detection of negated text (which affects negative sentiment prediction) still presents challenges. More research is needed on new forms of negation beyond prototypical negation cues such as “not” or “never.” The present research reports findings on the role of a set of words called “approximate negators,” namely “barely,” “hardly,” “rarely,” “scarcely,” and “seldom,” which, in specific occasions (such as attached to a word from the non-affirmative adverb “any” family), can operationalize negation styles not yet explored. Using a corpus of 6,500 tweets, human annotation allowed for the identification of 17 recurrent usages of these words as negatives (such as “very seldom”) which, along with findings from the literature, helped engineer specific features that guided a machine learning classifier in predicting negated tweets. The machine learning experiments also modeled negation scope (i.e. in which specific words are negated in the text) by employing lexical and dependency graph information. Promising results included F1 values for negation detection ranging from 0.71 to 0.89 and scope detection from 0.79 to 0.88. Future work will be directed to the application of these findings in automatic sentiment classification, further exploration of patterns in data (such as part-of-speech recurrences for these new types of negation), and the investigation of sarcasm, formal language, and exaggeration as themes that emerged from observations during corpus annotation.
","abstract_html":"<p>Although improvements have been made in the performance of sentiment analysis tools, the automatic detection of negated text (which affects negative sentiment prediction) still presents challenges. More research is needed on new forms of negation beyond prototypical negation cues such as “not” or “never.” The present research reports findings on the role of a set of words called “approximate negators,” namely “barely,” “hardly,” “rarely,” “scarcely,” and “seldom,” which, in specific occasions (such as attached to a word from the non-affirmative adverb “any” family), can operationalize negation styles not yet explored. Using a corpus of 6,500 tweets, human annotation allowed for the identification of 17 recurrent usages of these words as negatives (such as “very seldom”) which, along with findings from the literature, helped engineer specific features that guided a machine learning classifier in predicting negated tweets. The machine learning experiments also modeled negation scope (i.e. in which specific words are negated in the text) by employing lexical and dependency graph information. Promising results included F1 values for negation detection ranging from 0.71 to 0.89 and scope detection from 0.79 to 0.88. Future work will be directed to the application of these findings in automatic sentiment classification, further exploration of patterns in data (such as part-of-speech recurrences for these new types of negation), and the investigation of sarcasm, formal language, and exaggeration as themes that emerged from observations during corpus annotation.</p>","abstract_has_math":false,"creators":["Palomino, Norma E"],"institution":null,"degree_name":"Doctor of Professional Studies","degree_level":"Dissertation","degree_discipline":"School of Information Studies","degree_department":null,"school":null,"contributors":["Nancy McCracken"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018-05-13T07:00:00Z","date_published":"2018-05-13T07:00:00Z","updated_at":"2026-07-24T04:55:27Z","subjects":["dependency parsing","natural language processing","negation detection","sentiment analysis","social media data","Twitter","Social and Behavioral Sciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://surface.syr.edu/etd/867","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Nancy McCracken"]},{"key":"dc:creator","label":"Author","values":["Palomino, Norma E"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"thesis:degree_discipline","label":"Discipline","values":["School of Information Studies"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Professional Studies"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["dependency parsing","natural language processing","negation detection","sentiment analysis","social media data","Twitter","Social and Behavioral Sciences"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://surface.syr.edu/etd/867"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Although improvements have been made in the performance of sentiment analysis tools, the automatic detection of negated text (which affects negative sentiment prediction) still presents challenges. More research is needed on new forms of negation beyond prototypical negation cues such as “not” or “never.” The present research reports findings on the role of a set of words called “approximate negators,” namely “barely,” “hardly,” “rarely,” “scarcely,” and “seldom,” which, in specific occasions (such as attached to a word from the non-affirmative adverb “any” family), can operationalize negation styles not yet explored. Using a corpus of 6,500 tweets, human annotation allowed for the identification of 17 recurrent usages of these words as negatives (such as “very seldom”) which, along with findings from the literature, helped engineer specific features that guided a machine learning classifier in predicting negated tweets. The machine learning experiments also modeled negation scope (i.e. in which specific words are negated in the text) by employing lexical and dependency graph information. Promising results included F1 values for negation detection ranging from 0.71 to 0.89 and scope detection from 0.79 to 0.88. Future work will be directed to the application of these findings in automatic sentiment classification, further exploration of patterns in data (such as part-of-speech recurrences for these new types of negation), and the investigation of sarcasm, formal language, and exaggeration as themes that emerged from observations during corpus annotation.
"]},{"key":"dc:title","label":"Title","values":["The role of approximate negators in modeling the automatic detection of negation in tweets"]}]}],"canonical_facts":{"dc:contributor":["Nancy McCracken"],"dc:creator":["Palomino, Norma E"],"dc:description.abstract":["Although improvements have been made in the performance of sentiment analysis tools, the automatic detection of negated text (which affects negative sentiment prediction) still presents challenges. More research is needed on new forms of negation beyond prototypical negation cues such as “not” or “never.” The present research reports findings on the role of a set of words called “approximate negators,” namely “barely,” “hardly,” “rarely,” “scarcely,” and “seldom,” which, in specific occasions (such as attached to a word from the non-affirmative adverb “any” family), can operationalize negation styles not yet explored. Using a corpus of 6,500 tweets, human annotation allowed for the identification of 17 recurrent usages of these words as negatives (such as “very seldom”) which, along with findings from the literature, helped engineer specific features that guided a machine learning classifier in predicting negated tweets. The machine learning experiments also modeled negation scope (i.e. in which specific words are negated in the text) by employing lexical and dependency graph information. Promising results included F1 values for negation detection ranging from 0.71 to 0.89 and scope detection from 0.79 to 0.88. Future work will be directed to the application of these findings in automatic sentiment classification, further exploration of patterns in data (such as part-of-speech recurrences for these new types of negation), and the investigation of sarcasm, formal language, and exaggeration as themes that emerged from observations during corpus annotation.
"],"dc:identifier":["https://surface.syr.edu/etd/867"],"dc:subject":["dependency parsing","natural language processing","negation detection","sentiment analysis","social media data","Twitter","Social and Behavioral Sciences"],"dc:title":["The role of approximate negators in modeling the automatic detection of negation in tweets"],"thesis:degree_discipline":["School of Information Studies"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Doctor of Professional Studies"]},"updated_at":"2026-07-24T04:55:27Z"}