Frustrated, Polite, or Formal: Quantifying Feelings and Tone in Email

Email conversations are the primary mode of communication in enterprises. The email content expresses an individual’s needs, requirements and intentions. Affective information in the email text can be used to get an insight into the sender’s mood or emotion. We present a novel approach to model human frustration in text. We identify linguistic features that influence human perception of frustration and model it as a supervised learning task. The paper provides a detailed comparison across traditional regression and word distribution-based models. We report a mean-squared error (MSE) of 0.018 against human-annotated frustration for the best performing model. The approach establishes the importance of affect features in frustration prediction for email data. We further evaluate the efficacy of the proposed feature set and model in predicting other tone or affects in text, namely formality and politeness; results demonstrate a comparable performance against the state-of-the-art baselines.

[1]  Krzysztof Wegner,et al.  The Necessity of New Paradigms in Measuring Human-Chatbot Interaction , 2017 .

[2]  Jafar Adibi,et al.  Discovering important nodes through graph entropy the case of Enron email database , 2005, LinkKDD '05.

[3]  Maria Leonor Pacheco,et al.  of the Association for Computational Linguistics: , 2001 .

[4]  Bülent Yener,et al.  Graph Theoretic and Spectral Analysis of Enron Email Data , 2005, Comput. Math. Organ. Theory.

[5]  Saif Mohammad,et al.  Tracking Sentiment in Mail: How Genders Differ on Emotional Axes , 2011, WASSA@ACL.

[6]  Rohit J. Kate,et al.  Learning to Predict Readability using Diverse Linguistic Features , 2010, COLING.

[7]  Andrew Sears,et al.  Automated stress detection using keystroke and linguistic features: An exploratory study , 2009, Int. J. Hum. Comput. Stud..

[8]  Margaret L. Kern,et al.  Personality, Gender, and Age in the Language of Social Media: The Open-Vocabulary Approach , 2013, PloS one.

[9]  William A. Wallace,et al.  Automatic Text Analysis of Values in the Enron Email Dataset: Clustering a Social Network Using the Value Patterns of Actors , 2010, 2010 43rd Hawaii International Conference on System Sciences.

[10]  P. Ekman.  An argument for basic emotions , 1992 .

[11]  Shibamouli Lahiri,et al.  SQUINKY! A Corpus of Sentence-level Formality, Informativeness, and Implicature , 2015, ArXiv.

[12]  Hua Wang,et al.  Communicating emotions in online chat using physiological sensors and animated text , 2004, CHI EA '04.

[13]  Tong Wang,et al.  Automatic Acquisition of Lexical Formality , 2010, COLING.

[14]  James C. Lester,et al.  Modeling Learner Affect with Theoretically Grounded Dynamic Bayesian Networks , 2011, ACII.

[15]  Christopher A. Miller,et al.  Power and Politeness in Interactions: ADMIRE - A Tool for Deriving the Former from the Latter , 2012, 2012 International Conference on Social Informatics.

[16]  Jure Leskovec,et al.  A computational approach to politeness with application to social factors , 2013, ACL.

[17]  E.Y.A. Charles,et al.  A psychological based analysis of marketing email subject lines , 2016, 2016 Sixteenth International Conference on Advances in ICT for Emerging Regions (ICTer).

[18]  Erkki Sutinen,et al.  Are They Different? Affect, Feeling, Emotion, Sentiment, and Opinion Detection in Text , 2014, IEEE Transactions on Affective Computing.

[19]  Jerold L. Hale,et al.  The fundamental topoi of relational communication , 1984 .

[20]  Alfred O. Hero,et al.  Multi-Layer Graph Analysis for Dynamic Social Networks , 2013, IEEE Journal of Selected Topics in Signal Processing.

[21]  Arthur C. Graesser,et al.  Automatic detection of learner’s affect from conversational cues , 2008, User Modeling and User-Adapted Interaction.

[22]  Sisi Liu,et al.  A Hybrid Sentiment Analysis Framework for Large Email Data , 2015, 2015 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE).

[23]  Owen Rambow,et al.  Annotations for Power Relations on Email Threads , 2012, LREC.

[24]  Rafael A. Calvo,et al.  Affect Detection: An Interdisciplinary Review of Models, Methods, and Their Applications , 2010, IEEE Transactions on Affective Computing.

[25]  Robert Sigley,et al.  Text categories and where you can stick them : A crude formality index , 1997 .

[26]  Jana Diesner,et al.  Little bad concerns: Using sentiment analysis to assess structural balance in communication networks , 2015, 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).

[27]  Rachel Cotterill,et al.  Using Stylistic Features for Social Power Modeling , 2013 .

[28]  Terrill L. Frantz,et al.  Communication Networks from the Enron Email Corpus “It's Always About the People. Enron is no Different” , 2005, Comput. Math. Organ. Theory.

[29]  M. Seligman.  Flourish: A Visionary New Understanding of Happiness and Well-being , 2011 .

[30]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[31]  Joel R. Tetreault,et al.  An Empirical Analysis of Formality in Online Communication , 2016, TACL.

[32]  Sufal Das.  Sentiment Analysis for Web-based Big Data: A Survey , 2017 .

[33]  Saif Mohammad,et al.  NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweets , 2013, *SEMEVAL.

[34]  A. Mehrabian.  Basic dimensions for a general psychological theory : implications for personality, social, environmental, and developmental studies , 1980 .

[35]  Louise Guthrie,et al.  Towards the Orwellian Nightmare: Separation of Business and Personal Emails , 2006, ACL.

[36]  Ryan A. Rossi,et al.  Interactive Visual Graph Analytics on the Web , 2015, ICWSM.

[37]  Fei Xia,et al.  Email Formality in the Workplace: A Case Study on the Enron Corpus , 2011 .

[38]  Amy Beth Warriner,et al.  Norms of valence, arousal, and dominance for 13,915 English lemmas , 2013, Behavior Research Methods.

[39]  Jatinderkumar R. Saini,et al.  Emotion Detection and Sentiment Analysis in Text Corpus: A Differential Study with Informal and Formal Writing Styles , 2014 .

[40]  James C. Lester,et al.  Early Prediction of Student Frustration , 2007, ACII.

[41]  Cristina Conati,et al.  Empirically building and evaluating a probabilistic model of user affect , 2009, User Modeling and User-Adapted Interaction.