Using Syntactic and Semantic Context to Explore Psychodemographic Differences in Self-reference
33508Authors
nan
Abstract
Psychological analysis of language has repeat- edly shown that an individual’s rate of men- tioning 1st person singular pronouns predicts a wealth of important demographic and psy- chological factors. However, these analy- ses are performed out of context — syntac- tic and semantic — which may change the magnitude or even direction of such relation- ships. In this paper, we put “pronouns in their context”, exploring the relationship between self-reference and age, gender, and depres- sion depending on syntactic position and ver- bal governor. We find that pronouns are over- all more predictive when taking dependency relations and verb semantic categories into ac- count, and, the direction of the relationship can change depending on the semantic class of the verbal governor. 1
Keywords
Full Content
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2054–2059, Austin, Texas, November 1-5, 2016. c⃝2016 Association for Computational Linguistics Using Syntactic and Semantic Context to Explore Psychodemographic Differences in Self-reference Masoud Rouhizadeh†§, Lyle Ungar§, Anneke Buffone§, H Andrew Schwartz†§ †Stony Brook University, §University of Pennsylvania mrouhizadeh@gmail.com, ungar@cis.upenn.edu, buffonea@sas.upenn.edu, has@cs.stonybrook.edu Abstract Psychological analysis of language has repeat- edly shown that an individual’s rate of men- tioning 1st person singular pronouns predicts a wealth of important demographic and psy- chological factors. However, these analy- ses are performed out of context — syntac- tic and semantic — which may change the magnitude or even direction of such relation- ships. In this paper, we put “pronouns in their context”, exploring the relationship between self-reference and age, gender, and depres- sion depending on syntactic position and ver- bal governor. We find that pronouns are over- all more predictive when taking dependency relations and verb semantic categories into ac- count, and, the direction of the relationship can change depending on the semantic class of the verbal governor. 1 Introduction Approximately 1 in 18 English words on Face- book are first-person singular pronouns.1 Extensive work in psychological analyses of language has con- sistently found strong relation between first-person pronoun use and psychological attributes of individ- uals (Kendall, 1998; Pennebaker and Stone, 2003; Pennebaker, 2011; Twenge et al., 2012; Oishi et al., 2013; Carey et al., 2015). Although such find- ings have been replicated extensively, little is known about how the syntactic or semantic context of the pronouns may affect their relationship with human traits. Usage in subject or object position may 1Within the study dataset, 5.45% of all words from self- identified English speakers were first-person pronouns. vary, and the type of verb governing the reference may further change its relationship. For instance, while younger individuals are more likely to use 1st- person singular pronouns overall, older individuals may be more likely to use them as the subject of so- cial verbs. In this study we dive deep into this one type of word which makes up a large portion of our daily lives. We first look at the relationship between first person singular pronouns and age, gender, and de- pression. We then consider the syntactic position of the pronoun and its occurrence in the subject and direct object position. Next, we explore the self- referenced use of verbs compared to their general use across different semantic categories, followed by an examination of the rate of 1st-person singular pronoun as the subject and the object with different verb categories. We ultimately show that pronoun relationships with human outcomes can change drastically de- pending on their syntactic position and the category of their verbal governor. To be more specific, our contributions include: (a) taking the role of context into account in the psychological analysis of per- sonal pronouns, (b) distributional clustering of verbs using Canonical Correlation Analysis (CCA), and (c) exploring the integration of verbal semantic cat- egories in the analysis of pronouns. …
Content truncated to 500 words
Labeled Text
Psychological analysis of language has repeatedly shown that an individual’s rate of mentioning 1st person singular pronouns predicts a wealth of important demographic and psychological factors. However, these analyses are performed out of context — syntactic and semantic — which may change the magnitude or even direction of such relationships. In this paper, we put “pronouns in their context”, exploring the relationship between self-reference and age, gender, and depression depending on syntactic position and verbal governor. We find that pronouns are overall more predictive when taking dependency relations and verb semantic categories into account, and, the direction of the relationship can change depending on the semantic class of the verbal governor. 1
Publication Details
- Paper ID:
- 33508
- Year:
- 2016
- Publication:
- TIPSTER
- Publication Type:
- conf
- DOI:
- nan