Formalization and Modeling of Human Values for Recipient Sentiment Prediction

Formalization and Modeling of Human Values for Recipient Sentiment Prediction

Formalization and Modeling of Human Values for Recipient Sentiment Prediction Doctor of Philosophy OBINNA CHINEDU ONYIMADU Informatics Research Centre Henley Business School September 2017 Declaration I confirm that this is my own work and the use of all material from other sources has been properly and fully acknowledged. Obinna Chinedu Onyimadu ii Abstract Sentiment analysis is viewed generally as a text classification problem involving the prediction of the semantic orientation of a text. Much of the analysis has focused on the sentiment expressed in the sentence or by the writer but not the sentiment of the recipient. For example, the sentence “Housing costs have dropped significantly” might be assigned a negative classification by a sentiment analysis model, however humans from different works of life might express different sentiments. A landlord will likely express a negative sentiment while a renter might express a positive sentiment. Therefore, traditional sentiment analysis methods fail to capture the human centric aspects that motivate diverse sentiments. Additionally, attempts at predicting recipient sentiment have involved considerable human effort in the form of content analysis and empirical surveys, making the process expensive and time-consuming. Thus, the aim of this research is to develop a method of recipient sentiment analysis that is devoid of human input in the form of annotations or empirical surveys. The approach taken in this research involves applying a model of human values towards recipient sentiment prediction. The justification for this approach is based on the well-established principle that values influence human behaviour of which sentiment is a form. Therefore, if a persons’ values can be modelled quantitatively, when presented with some text, in theory the sentiment of the recipient can be predicted. This research proposes that the application of values in developing sentences is a generative process, that can be represented as a language model. A mechanism called Feature Switching (FS) that enables the determination of recipient’s sentiment from the value language model is also discussed. The resulting sentiment prediction model has an accuracy in the range of 72.2%-72.5% which is in and about the range of performance of existing systems which make use of content analysis and human annotated data. iii Acknowledgements I would like to express my gratitude to my supervisor, Dr Keiichi Nakata for his excellent supervision and support for making this thesis a reality. His invaluable suggestions and critical comments were key to the completion of this thesis. I would also like to acknowledge staff at the IRC and my friends for the many enlightening discussions we had at various points during this research. Finally, I want to acknowledge God almighty, without whom I would have been unable to complete this thesis. Obinna Chinedu Onyimadu September 2017 iv Dedications This thesis is dedicated to my parents, brothers and especially my wife. You all made the journey a lot easier and enjoyable. God Bless. v Table of Contents Declaration .............................................................................................................................. ii Abstract .................................................................................................................................. iii Acknowledgements.................................................................................................................iv Dedications .............................................................................................................................. v Table of Contents ....................................................................................................................vi LIST OF TABLES .....................................................................................................................xi LIST OF FIGURES ................................................................................................................ xiii 1. Introduction ..................................................................................................................... 1 1.1 Aims and Objectives ........................................................................................................ 3 1.2 Overview of Research Methodology .......................................................................... 4 1.3 Thesis Structure ........................................................................................................... 4 2. Sentiment Analysis as a Field of Study............................................................................... 6 2.1 Brief History of Sentiment Analysis ........................................................................... 6 2.2 SA Methods and Problems .......................................................................................... 8 2.3 Review of Author/Reader Stand Point ..................................................................... 12 2.3.1 Writer/Author Emotion and Stance .................................................................... 12 2.3.2 Recipient Emotion and Stance Detection ........................................................... 14 2.3.3 Socio-Theoretic Approaches ................................................................................. 15 2.4 Conclusion .................................................................................................................. 17 3. Values as a Field of Study .............................................................................................. 18 3.1 Definition of Values ................................................................................................... 18 3.2 Classification, Formalization and Application of Values ....................................... 19 3.3 Classification Methodology ...................................................................................... 21 3.3.1 Selection and Identification of Value Items ........................................................ 21 3.3.2 Categorization of items to inventories ................................................................ 22 3.4 Value Inventories ....................................................................................................... 22 3.4.1 Rokeach Value Survey (RVS) ................................................................................ 22 3.4.2 Schwartz Value Inventory (SVI) ........................................................................... 22 3.4.3 Personal Values Questionnaire (PVQ) ................................................................ 23 3.4.4 List of Values (LOV) .......................................................................................... 23 3.5 Building a Value Inventory ....................................................................................... 24 3.6 Conclusion .................................................................................................................. 26 4. Research Methodology ...................................................................................................... 27 4.1 DSR Methodology ...................................................................................................... 27 4.2 Design Steps ..................................................................................................................... 28 vi 4.2.1 Step 1: Awareness of problem ............................................................................... 29 4.2.2 Step 2: Suggestion .............................................................................................. 29 4.2.3 Step 3: Development .............................................................................................. 31 4.2.4 Step 4: Evaluation .............................................................................................. 31 4.2.5 Step 5: Conclusions ............................................................................................ 31 4.3 Conclusion .................................................................................................................. 31 5. Model Design – A model of Sentiment and Values .......................................................... 32 5.1 Characteristics of Values ........................................................................................... 32 5.2 Description of Value-Sentiment Model Processes ................................................. 33 5.3 Value Model – Decomposition of Values....................................................................... 36 5.4 VSM Parameter Identification of Value-Laden Utterances ................................... 40 5.4.1 Identifying Value Subject ...................................................................................... 42 5.4.2 Identifying Value Actions .................................................................................. 44 5.4.3 Identifying Value States ........................................................................................ 45 5.5 Complex Value Laden Sentences ............................................................................. 48 5.5.1 Compound Sentences ............................................................................................ 49 5.5.2 Complex Sentences ................................................................................................ 50 5.6 Structural Representation of Value Laden Sentences ............................................ 52

View Full Text

Details

  • File Type
    pdf
  • Upload Time
    -
  • Content Languages
    English
  • Upload User
    Anonymous/Not logged-in
  • File Pages
    259 Page
  • File Size
    -

Download

Channel Download Status
Express Download Enable

Copyright

We respect the copyrights and intellectual property rights of all users. All uploaded documents are either original works of the uploader or authorized works of the rightful owners.

  • Not to be reproduced or distributed without explicit permission.
  • Not used for commercial purposes outside of approved use cases.
  • Not used to infringe on the rights of the original creators.
  • If you believe any content infringes your copyright, please contact us immediately.

Support

For help with questions, suggestions, or problems, please contact us