Editorial for the 2nd AAAI-19 Workshop on A ective Content Analysis

Abstract

The A Con2019, the second AAAI Workshop on Affective Content Analysis @ AAAI-19 focused on the analysis of emotions, sentiments, and attitudes in textual, visual, and multimodal content for applications in psychology, consumer behavior, language understanding, and computer vision. It included the inaugural CL-A Shared Task on modeling happiness. The program comprised keynotes, original research presentations, a poster session, and presentations by the Shared Task winners.

Introduction

Workshop Topics and Format

The workshop presentations incorporated insights from psychologists, psycholinguists, and computer science researchers to develop new approaches that address open problems such as deep learning for a ect analysis, leveraging traditional a ective computing (multi-modal datasets), privacy concerns in a ect analysis, and inter-relationships between various a ect dimensions. These fall under the broad topics of interest of the workshop: { A ect and Cognitive Content Measurement in Text { Computational models for Consumer Behavior theories { Psycho{demographic Pro ling { A ect{based Text Generation { Spoken and Formal Language Comparison { Stylometrics, Typographics, and Psycho-linguistics { A ective needs and Consumer Behavior { Measurement and Evaluation of A ective Content { A ective Lexica for Online Marketing Communication { A ective human-agent, -computer, and-robot interaction { Multi-modal emotion recognition and sentiment analysis 3

Overview of the papers

The workshop featured four keynote talks, three paper sessions, and a poster session. 33 papers were submitted to the workshop, 11 of which were Systems for the CL-A shared task. Finally, 3 papers were accepted as full papers and 4 were accepted as posters, and these will be included in the proceedings. In addition, the winners from the CL-A task presented talks and posters at the workshop. One pre-published paper was also invited for the poster session.

The following sections brie y describe the keynote and sessions. 3.1

Keynotes

The workshop had a range of keynote speakers. Dr. Ellen Rilo 6 shared her work in the space of identifying a ective events and the reasons for their polarity. She introduced a ective events as experiences that positively or negatively impact on our lives and then discussed recent work on identifying a ective events and categorizing them based on the underlying reasons for their a ective polarity. The discussion included a description of a weakly supervised learning method to induce a large set of a ective events from a text corpus, learning models to classify a ective events based on Human Need Categories, and concluded with a discussion on directions of future work on this topic.

Dr. Alon Halevy 7 talked about a ective search. His talk was centered around the space of positive psychology. He described two works in this space that 6 http://www.cs.utah.edu/ rilo / 7 https://homes.cs.washington.edu/ alon/ develop new AI techniques for enabling technology that help individuals increase their well-being. The rst work was based on deriving insights from user's notes and second one explained a ective search in online ecommerce applications. His talk gave an insight towards potential applications of a ective analysis in real world applications.

Dr. Lyle Ungar 8 talked about the use of user generated content for a ect analysis. In this talk a study for computational modeling of empathy is presented. Social media language, combined with questionnaires is used to reveals that empathy has both 'good' (compassionate) and 'bad' (depleting) components, with 'bad' empathy associated with stress, reduced perceived control, and reduced well-being, all of which can be measured through peoples' social media language. He also discussed the utility of a novel annotation methodology in which subjects react to news stories both in free text and in multi-item questionnaire responses.

Last but not the least, Dr. Rada Mihalcea 9 discussed her work on grounded emotions. In this talk, she discussed several types of external factors and showed their impact and correlation with a users emotional state. Finally, she presented a study that proved that combining all extrinsic features leads to a decent predictive model for the emotional state of a user. 3.2

Papers:

The workshop included 3 full paper presentations and 4 posters.

Kowalczyk et. al [ 29 ] presented their work on privacy aware scalable polarity detection in Twitter. They rst argue that strict alignment of data acquisition, storage and analysis algorithms is necessary to avoid the common trade-o s between scalability, accuracy and privacy compliance. In their paper, they propose a new framework for acquisition of large-scale datasets, high accuracy supervisory signal and multilanguage sentiment prediction while respecting every privacy request applicable. Finally, a novel gradient boosting framework is proposed to achieve stateof- the-art results in virality ranking, already before including tweet's visual or propagation features. An empirical analysis across 18 languages shows the generality of this work.

Joshi et al [ 26 ] design a joint loss function to optimize the performance of Long Short Term Memory networks for predicting the valence from audio features in a dataset of Academy Award Movies. Drawing from psychology, they model arousal-valence interdependence in two ways and demonstrate a remarkable improvement in predicting valence over an independent valence model.

Qiu et al [ 57 ] work on multimodal emotion recognition with a new model they call \Adversarial and Cooperative Correlated Domain Adaptation". They demonstrate higher emotion classi cation accuracy on datasets comprising physiological signals and eye movements, by following a deep canonical correlation analysis approach that leverages the complementarity of multimodal signals. 8 http://www.cis.upenn.edu/ ungar/ 9 https://web.eecs.umich.edu/ mihalcea/ Their domain adaptation approach outperforms the state of the art approaches on the SEED IV dataset for four emotion tasks, as well as on the DEAP dataset for two dichotomies. 3.3

Posters

The paper by Tiam-Lee and Sumi [ 76 ] provides an analysis of the emotional experiences of students as they learn to program. They focus particularly on the transitions across di erent emotions and relate facial expressions, body posture and click logs in relation to emotional states. This preliminary study reported subjective di erences both in self-reported data and in the facial expressions automatically captured by the system, which highlights the need to design systems and experiments that are conscious of social and cultural norms.

The paper by Luo, Xu, and Chen [ 35 ] proposes an model to mine sentiment information in audio. It uses multiple traditional acoustic features and spectrum graphs, and is language insensitive as it focuses on acoustic features rather than audio features for modeling purposes. The authors report superior performance on the Multimodal Corpus of Sentiment Intensity dataset(MOSI) and Multimodal Opinion Utterances Dataset(MOUD) as compared to the state of the art.

The paper by Li, Rzepka, Ptaszynski, and Araki [ 31 ] reports on sentiment classi cation on Weibo developed on the basis of a custom-made Internet slang and emoticon lexicon derived from Weibo posts. The paper experiments with di erent parametric and non-parametric approaches to show the e ectiveness of their features for capturing humor, especially on the cases which are harder to classify as either positive or negative.

Last but not the least, Sun et. al [ 72 ] presented their pre-published work on converting a sentiment classi cation problem to image classi cation, through a method they call Super Characters which encodes each observation as an image, and then applies image processing approaches for sentiment classi cation. Given the pictogram nature of many widely-spoken languages, perhaps it is not surprising that Super Characters consistently outperforms other methods for sentiment classi cation and topic classi cation on datasets in four di erent languages { Chinese, Japanese, and Korean; however, Super Characters also reports a good performance on sentiment analysis on an English dataset of Amazon reviews. 3.4

CL-A

Shared Task

Eleven teams participated in Task 1 of the inaugural CL-A Shared Task AAAI19 and out of those, ve attempted Task 2. The best performing systems were submitted by The University of British Columbia, Canada [ 59 ], Arizona State University, USA [ 65 ], and the International Institute for Information Technology Hyderabad, India [ 73 ]. The Shared Task details are archived on Git 10 and the 10 https://github.com/kj2013/cla -happydb complete dataset is indexed on Harvard Dataverse 11. Shared Task participants showed creativity and ingenuity in modeling the problem in di erent vector spaces and enriching their training data with external resources. We believe that the widespread adoption of neural approaches for modeling Agency and Sociality and the stupendous performance even on the modest size of the dataset, are an indicator of the swift improvements happening in the eld of deep learning for text. In the future, we plan to release other resources complementary to the challenges of modeling a ect and emotion language from language. 4

Related Workshops

There is a growing number of workshops and conferences related to a ective computing which points to the importance of the research problem at hand, as well as the timeliness of this workshop for the AI community. The following workshops focused mainly on text analysis, sentiment, and subjectivity of the text content: { SENTIRE series: The workshop on Sentiment Elicitation from Natural Text for Information Retrieval and Extraction has been a continuing series for the past few years at ICDM 12. The organizers of this workshop series are part of the program committee for the proposed workshop. { WASSA: The workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis is a workshop series that concentrates on sentiment analysis in text and looks at various aspect{based and subjectivity analysis of text in that context. The workshop has been a popular workshop at top NLP conferences such as EMNLP, ACL, and NAACL in recent years 13. The organizers of this workshop series as well are a part of the program committee of this proposed workshop.

The following workshops focused on the multi-modal, sensory data in their analysis. Text and language analysis is however not the focus of these workshops. This makes the AAAI Workshop on A ective Content Analysis rather unique in its pitch to bring the two communities together.

{ The rst workshop on A ective Computing (IJCAI 2017) concentrates on measuring human a ects based on sensors and wearable devices. { 1st Workshop on Tools and Algorithms for Mental Health and Wellbeing,

Pain, and Distress (MHWPD) { Multimodal Emotion Recognition Challenge (MEC 2017) @ 2018 Asian Conference on A ective Computing and Intelligent Interaction (AACII) Other current relevant events include ACII14, HUMANAIZE15, and NLP+CSS16. 11 DOI:10.7910/DVN/JZAS66; https://goo.gl/3rcZqf 12 http://sentic.net/sentire/ 13 http://optima.jrc.it/wassa2017/ 14 http://acii2017.org/ 15 http://st.sigchi.org/publications/toc/humanize-2017.html 16 https://sites.google.com/site/nlpandcss/nlp-css-at-acl-2017

Outlook

This workshop received a promising number of submissions and generated a lot of interest from scholars and industry. The response to the Shared Task was also successful at identifying a community of researchers and a variety of resources for a ect analysis in text. The program comprising interdisciplinary keynotes, original research presentations, a poster session and a Shared Task has proven to be a successful and agile format. We will continue this multi{disciplinary workshop in an attempt to establish the space of computational approaches for a ective content analysis.

Acknowledgments

We would like to thank Adobe Research for their generous funding which made this workshop possible. We thank our program committee members who did an excellent job of reviewing the submissions. All PC members are documented on the A Con-19 website17. 17 https://sites.google.com/view/a con2019/committees 82. Zahiri, S., Choi, J.: Emotion Detection on TV Show Transcripts with Sequencebased Convolutional Neural Networks. In: Proceedings of the AAAI-18 Workshop on A ective Content Analysis, New Orleans, USA, AAAI (2018) 83. Zhao, S., Yao, H., Jiang, X.: Predicting continuous probability distribution of image emotions in valence-arousal space. In: Proceedings of the 23rd ACM International Conference on Multimedia. MM '15, New York, NY, USA, ACM (2015) 879{882

References

1. Berry , M.W. , Browne , M. , Signer , B. : Topic annotated enron email data set . Philadelphia: Linguistic Data Consortium ( 2001 )

2. Bestgen , Y. : Building a ective lexicons from speci c corpora for automatic sentiment analysis . In: LREC . ( 2008 )

3. Bestgen , Y. , Vincze , N.: Checking and bootstrapping lexical norms by means of word similarity indexes . Behavior Research Methods 44 ( 4 ) ( 2012 ) 998 { 1006

4. Bird , S. : Nltk: The natural language toolkit . In: Proceedings of the COLING/ACL on Interactive presentation sessions, Association for Computational Linguistics ( 2006 ) 69 { 72

5. Blei , D.M. , Ng , A.Y. , Jordan , M.I. : Latent dirichlet allocation . Journal of Machine Learning Research 3(Jan) ( 2003 ) 993 { 1022

6. Blitzer , J. , Dredze , M. , Pereira , F. , et al.: Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classi cation . In: ACL . Volume 7 . ( 2007 ) 440 { 447

7. Bradley , M.M. , Lang , P.J.: A ective norms for english words (anew): Instruction manual and a ective ratings . Technical report, Technical report C-1 , the center for research in psychophysiology, University of Florida ( 1999 )

8. Brett , D. , Pinna , A. : The distribution of a ective words in a corpus of newspaper articles . Procedia-Social and Behavioral Sciences 95 ( 2013 ) 621 { 629

9. Cambria , E. , Fu , J. , Bisio , F. , Poria , S.: A ectivespace 2: Enabling a ective intuition for concept-level sentiment analysis . In: AAAI . ( 2015 ) 508 { 514

10. Chhaya , N. , Jaidka , K. , Ungar , L.H. : The AAAI-18 Workshop on A ective Content Analysis . In: Proceedings of the AAAI-18 Workshop on A ective Content Analysis , New Orleans, USA, AAAI ( 2018 )

11. Chikersal , P. , Poria , S. , Cambria , E. , Gelbukh , A. , Siong , C.E. : Modelling public sentiment in twitter: using linguistic patterns to enhance supervised learning . In: International Conference on Intelligent Text Processing and Computational Linguistics , Springer ( 2015 ) 49 { 65

12. Cohen , W.W. : Enron email dataset . ( 2009 )

13. Colombetti , G.: From a ect programs to dynamical discrete emotions . Philosophical Psychology 22 ( 4 ) ( 2009 ) 407 { 425

14. Danescu-Niculescu-Mizil , C. , Sudhof , M. , Jurafsky , D. , Leskovec , J. , Potts , C. : A computational approach to politeness with application to social factors . arXiv preprint arXiv:1306.6078 ( 2013 )

15. Derakhshan , A. , Mikaeili , M. , Gedeon , T. : Discriminating Between Truthfulness and Deception Using Infrared Thermal Imaging and Peripheral Physiology . ( 2018 )

16. Ding , H. , Jiang , T. , Rilo , E.: Why is an Event A ective? Classifying A ective Events based on Human Needs . In: Proceedings of the AAAI-18 Workshop on A ective Content Analysis , New Orleans, USA, AAAI ( 2018 )

17. Dragut , E.C. , Yu , C. , Sistla , P. , Meng , W. : Construction of a sentimental word dictionary . In: Proceedings of the 19th ACM International Conference on Information and Knowledge Management. CIKM '10 , New York, NY, USA, ACM ( 2010 ) 1761 { 1764

18. Dumpala , S.H. , Chakraborty , R. , Kopparapu , S.K. : Knowledge driven feed-forward neural network for audio a ective content analysis . In: Proceedings of the AAAI-18 Workshop on A ective Content Analysis , New Orleans, USA, AAAI ( 2018 )

19. Ekman , P.: An argument for basic emotions . Cognition & Emotion 6 ( 3 -4) ( 1992 ) 169 { 200

20. Esuli , A. , Sebastiani , F. : Sentiwordnet: A publicly available lexical resource for opinion mining . In: Proceedings of LREC. Volume 6 ., Citeseer ( 2006 ) 417 { 422

21. Hatzivassiloglou , V. , McKeown , K.R. : Predicting the semantic orientation of adjectives . In: Proceedings of the eighth conference on European chapter of the Association for Computational Linguistics, Association for Computational Linguistics ( 1997 ) 174 { 181

22. He , S. , Ballard , D. , Gildea , D. : Building and tagging with an a ect lexicon . ( 2004 )

23. Hu , C. , Walker , M.A. , Ne , M. , Tree , J.E.F. : Storytelling agents with personality and adaptivity . In: International Conference on Intelligent Virtual Agents , Springer ( 2015 ) 181 { 193

24. Huang , C. r.: Ontology and the Lexicon: A Natural Language Processing Perspective . Cambridge University Press ( 2010 )

25. Jones , E. , Oliphant , T. , Peterson , P. , et al.: SciPy: Open source scienti c tools for Python ( 2001 {) [Online; accessed 2017- 01 -17].

26. Joshi , T. , Sivaprasad , S. , Pedanekar , N.: Partners in Crime: Utilizing ArousalValence Relationship for Continuous Prediction of Valence in Movies . In: Proceedings of the AAAI-19 Workshop on A ective Content Analysis , Honolulu, USA, AAAI ( 2019 )

27. Kanayama , H. , Nasukawa , T. : Fully automatic lexicon expansion for domainoriented sentiment analysis . In: Proceedings of the 2006 conference on empirical methods in natural language processing , Association for Computational Linguistics ( 2006 ) 355 { 363

28. Kanayama , H. , Nasukawa , T. : Fully automatic lexicon expansion for domainoriented sentiment analysis . In: Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing. EMNLP '06 , Stroudsburg , PA, USA, Association for Computational Linguistics ( 2006 ) 355 { 363

29. Kowalczyk , D. , Larsen , J.: Scalable Privacy-Compliant Virality Prediction on Twitter. In: Proceedings of the AAAI-19 Workshop on A ective Content Analysis , Honolulu, USA, AAAI ( 2019 )

30. Le , H. , Cerisara , C. , Denis , A. : Do convolutional networks need to be deep for Text Classi cation . In: Proceedings of the AAAI-18 Workshop on A ective Content Analysis , New Orleans, USA, AAAI ( 2018 )

31. Li , D. , Rzepka , R. , Ptaszynski , M. , Araki , K. : Audio Sentiment Analysis by Heterogeneous Signal Features Learned from Utterance-Based Parallel Neural Network . In: Proceedings of the AAAI-19 Workshop on A ective Content Analysis , Honolulu, USA, AAAI ( 2019 )

32. Litvinova , T. , Litvinova , O. , Seredin , P. , Zagorovskaya , O. : RusNeuroPsych: Corpus for Study Relations Between Author Demo-graphic, Personality Traits, Lateral Preferences and A ect in Text . ( 2018 )

33. Liu , T. , Kappas , A. : Predicting Engagement Breakdown in HRI Using Thin-slices of Facial Expressions . In: Proceedings of the AAAI-18 Workshop on A ective Content Analysis , New Orleans, USA, AAAI ( 2018 )

34. Lu , Y. , Castellanos , M. , Dayal , U. , Zhai , C. : Automatic construction of a contextaware sentiment lexicon: An optimization approach . In: Proceedings of the 20th International Conference on World wide web, ACM ( 2011 ) 347 { 356

35. Luo , Z. , Xu , H. , Chen , F. : Audio Sentiment Analysis by Heterogeneous Signal Features Learned from Utterance-Based Parallel Neural Network . In: Proceedings of the AAAI-19 Workshop on A ective Content Analysis , Honolulu, USA, AAAI ( 2019 )

36. Maheshwari , T. , Reganti , A.N. , Kumar , U. , Chakraborty , T. , Das , A. : Semantic interpretation of social network communities . In: AAAI . ( 2017 ) 4967 { 4968

37. Mairesse , F. , Walker , M.A. : Trainable generation of big- ve personality styles through data-driven parameter estimation . In: ACL . ( 2008 ) 165 { 173

38. Manning , C.D. , Surdeanu , M. , Bauer , J. , Finkel , J.R. , Bethard , S. , McClosky , D. : The stanford corenlp natural language processing toolkit . In: ACL (System Demonstrations) . ( 2014 ) 55 { 60

39. Mehrabian , A. : Basic dimensions for a general psychological theory implications for personality, social, environmental, and developmental studies . ( 1980 )

40. Miller , G.A. : Wordnet: a lexical database for english . Communications of the ACM 38 ( 11 ) ( 1995 ) 39 { 41

41. Mitchell, S. , OSullivan, M. , Dunning , I. : Pulp: A linear programming toolkit for python . The University of Auckland, Auckland, New Zealand, http://www. optimization-online. org/DB FILE/ 2011 /09/3178. pdf ( 2011 )

42. Mohammad , S.M. : # emotional tweets . In: Proceedings of the First Joint Conference on Lexical and Computational Semantics-Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation , Association for Computational Linguistics ( 2012 ) 246 { 255

43. Mohammad , S.M. , Turney , P.D.: Emotions evoked by common words and phrases: Using mechanical turk to create an emotion lexicon . In: Proceedings of the NAACL HLT 2010 workshop on computational approaches to analysis and generation of emotion in text, Association for Computational Linguistics ( 2010 ) 26 { 34

44. Mohammad , S.M. , Turney , P.D.: Crowdsourcing a word-emotion association lexicon . 29 ( 3 ) ( 2013 ) 436 { 465

45. Mohammad , S.M. , Turney , P.D.: Nrc emotion lexicon . Technical report, NRC Technical Report ( 2013 )

46. Muhammad , A. , Wiratunga , N. , Lothian , R. , Glassey , R.: Domain-based lexicon enhancement for sentiment analysis . In: SMA@ BCS-SGAI . ( 2013 ) 7 { 18

47. Nester , D. , Haduong , N. , Vaidyanathan , P. , Prud'Hommeaux , E. , Bailey , R. , Alm , C. : Multimodal Alignment for A ective Content . In: Proceedings of the AAAI-18 Workshop on A ective Content Analysis , New Orleans, USA, AAAI ( 2018 )

48. Nielsen , F.A.: A new anew: Evaluation of a word list for sentiment analysis in microblogs . arXiv preprint arXiv:1103.2903 ( 2011 )

49. Pavlick , E. , Tetreault , J.: An empirical analysis of formality in online communication . Transactions of the Association for Computational Linguistics 4 ( 2016 ) 61 { 74

50. Pennebaker , J.W. , Francis , M.E. , Booth , R.J.: Linguistic inquiry and word count: Liwc 2001 . Mahway: Lawrence Erlbaum Associates 71 ( 2001 ) 2001

51. Peterson , K. , Hohensee , M. , Xia , F. : Email formality in the workplace: A case study on the enron corpus . In: Proceedings of the Workshop on Languages in Social Media, Association for Computational Linguistics ( 2011 ) 86 { 95

52. Picard , R.W. , Picard , R.: A ective computing . Volume 252 . MIT press Cambridge ( 1997 )

53. Pittman , M. , Reich, B.: Social media and loneliness: Why an instagram picture may be worth more than a thousand twitter words . Computers in Human Behavior 62 ( 2016 ) 155 { 167

54. Plutchik , R.: A general psychoevolutionary theory of emotion . Theories of Emotion 1 ( 1980 ) 3 { 31

55. Preotiuc-Pietro , D. , Xu , W. , Ungar , L.H. : Discovering user attribute stylistic differences via paraphrasing . In: Proceedings of the Thirtieth AAAI Conference on Arti cial Intelligence , February 12-17 , 2016 , Phoenix, Arizona, USA. ( 2016 ) 3030 { 3037

56. Qiu , G. , Liu , B. , Bu , J. , Chen , C. : Opinion word expansion and target extraction through double propagation . Computational linguistics 37(1) ( 2011 ) 9 { 27

57. Qiu , J. , Chen , X. , Hu , K. : A Novel Machine Learning-based Sentiment Analysis Method for Chinese Social Media Considering Chinese Slang Lexicon and Emoticons . In: Proceedings of the AAAI-19 Workshop on A ective Content Analysis , Honolulu, USA, AAAI ( 2019 )

58. Rahimtoroghi , E. , Wu , J. , Wang , R. , Anand , P. , Walker , M.A. : Modelling protagonist goals and desires in rst-person narrative . arXiv preprint arXiv:1708.09040 ( 2017 )

59. Rajendran , A. , Zhang , C. , Abdul-Mageed , M. : Happy together: Learning and understanding appraisal from natural language . In: Proceedings of the 2nd Workshop on A ective Content Analysis @ AAAI (A Con2019) , Honolulu, Hawaii ( January 2019 )

60. Ranganath , R. , Jurafsky , D. , McFarland , D.A. : Detecting friendly, irtatious, awkward, and assertive speech in speed-dates . Computer Speech & Language 27 ( 1 ) ( 2013 ) 89 { 115

61. Reed , L. , Wu , J. , Oraby , S. , Anand , P. , Walker , M. : Learning lexico-functional patterns for rst-person a ect . arXiv preprint arXiv:1708.09789 ( 2017 )

62. Ribeiro , F.N. , Araujo , M. , Goncalves , P. , Goncalves , M.A. , Benevenuto , F. : Sentibench-a benchmark comparison of state-of-the-practice sentiment analysis methods . EPJ Data Science 5 ( 1 ) ( 2016 ) 1 { 29

63. Robertson , S. : Understanding inverse document frequency: On theoretical arguments for idf . Journal of Documentation 60 ( 5 ) ( 2004 ) 503 { 520

64. Sakaguchi , K. , Duh , K. , Post , M. , Van Durme , B. : Robsut wrod reocginiton via semi-character recurrent neural network . In: AAAI . ( 2017 ) 3281 { 3287

65. Saxon , M. , Bhandari , S. , Ruskin , L. , Honda , G.: Word pair convolutional model for happy moment classi cation . In: Proceedings of the 2nd Workshop on A ective Content Analysis @ AAAI (A Con2019) , Honolulu, Hawaii ( January 2019 )

66. Schwartz , H.A. , Eichstaedt , J.C. , Kern , M.L. , Dziurzynski , L. , Ramones , S.M. , Agrawal , M. , Shah , A. , Kosinski , M. , Stillwell , D. , Seligman , M.E. , et al.: Personality, gender, and age in the language of social media: The open-vocabulary approach . PloS One 8 ( 9 ) ( 2013 ) e73791

67. Seligman , M.E. : Flourish: a visionary new understanding of happiness and wellbeing . Policy 27 ( 3 ) ( 2011 ) 60 { 1

68. Stackover ow: Finding the best trade-o point on a curve ( 2015 )

69. Stone , P.J. , Dunphy , D.C. , Smith , M.S.: The general inquirer: A computer approach to content analysis . ( 1966 )

70. Strapparava , C. , Mihalcea , R.: Semeval-2007 task 14: A ective text . In: Proceedings of the 4th International Workshop on Semantic Evaluations, Association for Computational Linguistics ( 2007 ) 70 { 74

71. Strapparava , C. , Valitutti , A. , et al.: Wordnet a ect: an a ective extension of wordnet . In: LREC . Volume 4 . ( 2004 ) 1083 { 1086

72. Sun , B. , Yang , L. , Dong , P. , Zhang, W. , Dong , J. , Young , C. : Super Characters: A Conversion from Sentiment Classi cation to Image Classi cation . In: Proceedings of the AAAI-19 Workshop on A ective Content Analysis , Honolulu, USA, AAAI ( 2019 )

73. Syed , B. , Indurthi , V. , Shah , K. , Gupta , M. , Varma , V. : Ingredients for happiness: Modeling constructs via semi-supervised content driven inductive transfer learning . In: Proceedings of the 2nd Workshop on A ective Content Analysis @ AAAI (A Con2019) , Honolulu, Hawaii ( January 2019 )

74. Taboada , M. , Brooke , J. , To loski, M., Voll , K. , Stede , M. : Lexicon-based methods for sentiment analysis . Computational Linguistics 37 ( 2 ) ( 2011 ) 267 { 307

75. Thelwall , M. , Buckley , K. , Paltoglou , G. , Skowron , M. , Garcia , D. , Gobron , S. , Ahn , J. , Kappas , A. , Kuster, D. , Holyst , J.A. : Damping sentiment analysis in online communication: discussions, monologs and dialogs . In: International Conference on Intelligent Text Processing and Computational Linguistics , Springer ( 2013 ) 1 { 12

76. Tiam-Lee , J. , Sumi , K. : Emotional Experience of Students Interacting with a System for Learning Programming . In: Proceedings of the AAAI-19 Workshop on A ective Content Analysis , Honolulu, USA, AAAI ( 2019 )

77. Tighe , E.P. , Ureta , J.C. , Pollo , B.A.L. , Cheng, C.K., de Dios Bulos , R.: Personality trait classi cation of essays with the application of feature reduction . In: SAAIP@ IJCAI . ( 2016 ) 22 { 28

78. Turney , P.D. , Littman , M.L. : Measuring praise and criticism: Inference of semantic orientation from association . ACM Transactions on Information Systems (TOIS) 21(4) ( 2003 ) 315 { 346

79. Warriner , A.B. , Kuperman , V. , Brysbaert , M. : Norms of valence, arousal, and dominance for 13,915 english lemmas . Behavior research methods 45(4) ( 2013 ) 1191 { 1207

80. Wiebe , J. , Wilson, T. , Bell , M. : Identifying collocations for recognizing opinions . In: Proceedings of the ACL-01 Workshop on Collocation: Computational Extraction , Analysis, and Exploitation. ( 2001 ) 24 { 31

81. Wu , J. , Walker , M. , Anand , P. , Whittaker , S. : Linguistic re exes of well-being and happiness in echo . In: Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis. ( 2017 ) 81 { 91