Human Needs Categorization of Affective Events Using Labeled and Unlabeled Data

We often talk about events that impact us positively or negatively. For example “I got a job” is good news, but “I lost my job” is bad news. When we discuss an event, we not only understand its affective polarity but also the reason why the event is beneficial or detrimental. For example, getting or losing a job has affective polarity primarily because it impacts us financially. Our work aims to categorize affective events based upon human need categories that often explain people’s motivations and desires: PHYSIOLOGICAL, HEALTH, LEISURE, SOCIAL, FINANCIAL, COGNITION, and FREEDOM. We create classification models based on event expressions as well as models that use contexts surrounding event mentions. We also design a co-training model that learns from unlabeled data by simultaneously training event expression and event context classifiers in an iterative learning process. Our results show that co-training performs well, producing substantially better results than the individual classifiers.

[1]  Rada Mihalcea,et al.  Co-training and Self-training for Word Sense Disambiguation , 2004, CoNLL.

[2]  Mihai Surdeanu,et al.  The Stanford CoreNLP Natural Language Processing Toolkit , 2014, ACL.

[3]  Slav Petrov,et al.  Globally Normalized Transition-Based Neural Networks , 2016, ACL.

[4]  Xiaojin Zhu,et al.  May All Your Wishes Come True: A Study of Wishes and How to Recognize Them , 2009, NAACL.

[5]  Ellen Riloff,et al.  Extracting Information about Medication Use from Veterinary Discussions , 2015, NAACL.

[6]  Ellen Riloff,et al.  Acquiring Knowledge of Affective Events from Blogs Using Label Propagation , 2016, AAAI.

[7]  Marilyn A. Walker,et al.  Learning Lexico-Functional Patterns for First-Person Affect , 2017, ACL.

[8]  R. Swanson,et al.  Identifying Personal Stories in Millions of Weblog Entries , 2009, ICWSM 2009.

[9]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[10]  Elahe Rahimtoroghi,et al.  Modelling Protagonist Goals and Desires in First-Person Narrative , 2017, SIGDIAL Conference.

[11]  Avrim Blum,et al.  The Bottleneck , 2021, Monopsony Capitalism.

[12]  Dan Goldwasser,et al.  Ask, and Shall You Receive? Understanding Desire Fulfillment in Natural Language Text , 2016, AAAI.

[13]  A. Maslow.  Motivation and Personality , 1954 .

[14]  Janyce Wiebe,et al.  +/-EffectWordNet: Sense-level Lexicon Acquisition for Opinion Inference , 2014, EMNLP.

[15]  Hal Daumé,et al.  A Co-training Approach for Multi-view Spectral Clustering , 2011, ICML.

[16]  Ellen Riloff,et al.  A COMPUTATIONAL MODEL FOR PLOT UNITS , 2013, Comput. Intell..

[17]  Claire Cardie,et al.  Major Life Event Extraction from Twitter based on Congratulations/Condolences Speech Acts , 2014, EMNLP.

[18]  Arjun Mukherjee,et al.  Extracting Verb Expressions Implying Negative Opinions , 2015, AAAI.

[19]  Yejin Choi,et al.  Connotation Frames: A Data-Driven Investigation , 2015, ACL.

[20]  Manfred A. Max-Neef.  Human Scale Development: Conception, Application and Further Reflections , 1989 .

[21]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[22]  Xiaojun Wan,et al.  Co-Training for Cross-Lingual Sentiment Classification , 2009, ACL.

[23]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[24]  Ellen Riloff,et al.  Exploiting Strong Syntactic Heuristics and Co-Training to Learn Semantic Lexicons , 2002, EMNLP.

[25]  Eugene Charniak,et al.  Effective Self-Training for Parsing , 2006, NAACL.

[26]  Ellen Riloff,et al.  Automatically Producing Plot Unit Representations for Narrative Text , 2010, EMNLP.

[27]  Janyce Wiebe,et al.  Benefactive/Malefactive Event and Writer Attitude Annotation , 2013, ACL.

[28]  James W. Pennebaker,et al.  Linguistic Inquiry and Word Count (LIWC2007) , 2007 .

[29]  Tomoki Toda,et al.  Acquiring a Dictionary of Emotion-Provoking Events , 2014, EACL.

[30]  Ellen Riloff,et al.  Why Is an Event Affective? Classifying Affective Events Based on Human Needs , 2018, AAAI Workshops.

[31]  Ellen Riloff,et al.  Weakly Supervised Induction of Affective Events by Optimizing Semantic Consistency , 2018, AAAI.

[32]  Janyce Wiebe,et al.  Sentiment Propagation via Implicature Constraints , 2014, EACL.

[33]  Janyce Wiebe,et al.  Joint Prediction for Entity/Event-Level Sentiment Analysis using Probabilistic Soft Logic Models , 2015, EMNLP.

[34]  Roger C. Schank,et al.  Scripts, plans, goals and understanding: an inquiry into human knowledge structures , 1978 .

[35]  Cheng Wang,et al.  Co-training for Semi-supervised Sentiment Classification Based on Dual-view Bags-of-words Representation , 2015, ACL.