{"type":"ScholarlyArticle","title":"Towards the Quantitative Interpretability Analysis of Citizens Happiness Prediction","authors":[{"name":"Lin Li","slug":"lin-li","given":"Lin","family":"Li","affiliation":"Wuhan University of Technology , Wuhan , China"},{"name":"Xiaohua Wu","slug":"xiaohua-wu","given":"Xiaohua","family":"Wu","affiliation":"Wuhan University of Technology , Wuhan , China"},{"name":"Miao Kong","slug":"miao-kong","given":"Miao","family":"Kong","affiliation":"Wuhan University of Technology , Wuhan , China"},{"name":"Dong Zhou","slug":"dong-zhou","given":"Dong","family":"Zhou","affiliation":"Hunan University of Science and Technology , Xiangtan , China"},{"name":"Xiaohui Tao","slug":"xiaohui-tao","given":"Xiaohui","family":"Tao","affiliation":"University of Southern Queensland , Queensland , Australia"}],"abstract":"Evaluating the high-effect factors of citizens' happiness is beneficial to a wide range of policy-making for economics and politics in most countries. Benefiting from the high-efficiency of regression models, previous efforts by sociology scholars have analyzed the effect of happiness factors with high interpretability. However, restricted to their research concerns, they are specifically interested in some subset of factors modeled as linear functions. Recently, deep learning shows promising prediction accuracy while addressing challenges in interpretability. To this end, we introduce Shapley value that is inherent in solid theory for factor contribution interpretability to work with deep learning models by taking into account interactions between multiple factors. The proposed solution computes the Shapley value of a factor, i.e., its average contribution to the prediction in different coalitions based on coalitional game theory. Aiming to evaluate the interpretability quality of our solution, experiments are conducted on a Chinese General Social Survey (CGSS) questionnaire dataset. Through systematic reviews, the experimental results of Shapley value are highly consistent with academic studies in social science, which implies our solution for citizens' happiness prediction has 2-fold implications, theoretically and practically.","doi":"10.24963/ijcai.2022/707","url":"https://ijcai.org/proceedings/2022/707","pdf":"https://ijcai.org/proceedings/2022/0707.pdf","markdown":"https://ijcai.org/proceedings/2022/707.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/707","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Research Papers","track":"AI for Good","number":707,"pages":{"first":5094,"last":5100},"keywords":["AI Ethics, Trust, Fairness: Societal Impact of AI","Machine Learning: Explainable/Interpretable Machine Learning","AI Ethics, Trust, Fairness: Explainability and Interpretability","Humans and AI: Computational Sustainability and Human Well-Being"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38987148","length_sec":71,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985291","length_sec":527,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Aas et al., 2021] Kjersti Aas, Martin Jullum, and Anders Løland. Explaining individual predictions when features are dependent: More accurate approximations to shapley values. Artif. Intell., 298:103502, 2021.","title":"Explaining individual predictions when features are dependent: More accurate approximations to shapley values","authors":"Kjersti Aas, Martin Jullum, Anders Løland","year":"2021","venue":"Artif. Intell","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Baucells and Sarin, 2007] Manel Baucells and Rakesh K. Sarin. Satiation in discounted utility. Oper. Res., 55(1):170-181, 2007.","title":"Satiation in discounted utility","authors":"Manel Baucells, K Rakesh, Sarin","year":"2007","venue":"Oper. Res","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Binder and Broekel, 2012] Martin Binder and Broekel. Happiness no matter the cost? an examination on how efficiently individ- uals reach their happiness levels. Journal of Happiness Studies, 13(4):621-645, 2012.","title":"Happiness no matter the cost? an examination on how efficiently individuals reach their happiness levels","authors":"Martin Binder, Broekel","year":"2012","venue":"Journal of Happiness Studies","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cheng et al., 2016] Heng-Tze Cheng, Levent Koc, and Jeremiah Harmsen et al. Wide & deep learning for recom- mender systems. In DLRS@RecSys, pages 7-10, 2016.","title":"Wide & deep learning for recommender systems","authors":"Heng-Tze Cheng, Levent Koc, Jeremiah Harmsen","year":"2016","venue":"DLRS@RecSys","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cordero-Ferrera et al., 2017] José Manuel Cordero-Ferrera, Javier Salinas-Jiménez, and M. Mar Salinas-Jiménez. Exploring fac- tors affecting the level of happiness across countries: A condi- tional robust nonparametric frontier analysis. Eur. J. Oper. Res., 256(2):663-672, 2017.","title":"José Manuel Cordero-Ferrera, Javier Salinas-Jiménez, and M. Mar Salinas-Jiménez. Exploring factors affecting the level of happiness across countries: A conditional robust nonparametric frontier analysis","authors":"Cordero-Ferrera","year":"2017","venue":"Eur. J. Oper. Res","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Daswani and Leike, 2015] Mayank Daswani and Jan Leike. A def- inition of happiness for reinforcement learning agents. In Artifi- cial General Intelligence, volume 9205, pages 231-240, 2015.","title":"A definition of happiness for reinforcement learning agents","authors":"Mayank Daswani, Jan Leike","year":"2015","venue":"Artificial General Intelligence","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Deng, 2019] Min Deng. Social relationships, mental health and well-being of the elderly: an empirical analysis based on cgss2015. population and development, 25(3):85-93, 2019.","title":"Social relationships, mental health and well-being of the elderly: an empirical analysis based on cgss2015","authors":"Min Deng","year":"2019","venue":"population and development","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Di, 2018] Feifei Di. A study on the relationship between chinese residents behavioral attitude, lifestyle well-being and environ- mental behavior-based on cgss2013. Journal of Arid Land re- sources and Environment, 032(003):7-11, 2018.","title":"A study on the relationship between chinese residents behavioral attitude, lifestyle well-being and environmental behavior-based on cgss2013","authors":"Feifei Di","year":"2018","venue":"Journal of Arid Land resources and Environment","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Durante et al., 2015] Durante, Daniele, and Paganin et al. Bayesian modeling of networks in complex business intelligence problems. J. R. Stat. Soc., C: Appl. Stat., 66:555-580, 2015.","title":"Bayesian modeling of networks in complex business intelligence problems","authors":"Daniele Durante, Paganin","year":"2015","venue":"J. R. Stat. Soc., C: Appl. Stat","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Egilmez et al., 2019] Gokhan Egilmez, Nadiye Özlem Erdil, and Omid Mohammadi Arani et al. Application of artificial neural networks to assess student happiness. Int. J. Appl. Decis. Sci., 12(2):115-140, 2019.","title":"Application of artificial neural networks to assess student happiness","authors":"Gokhan Egilmez, Nadiye Özlem Erdil, Omid Mohammadi, Arani","year":"2019","venue":"Int. J. Appl. Decis. Sci","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Frey and Stutzer, 2012] Bruno S. Frey and Alois Stutzer. The use of happiness research for public policy. Soc. Choice Welf., 38(4):659-674, 2012.","title":"The use of happiness research for public policy","authors":"Bruno S Frey, Alois Stutzer","year":"2012","venue":"Soc. Choice Welf","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Garaigordobil, 2015] Maite Garaigordobil. Predictor variables of happiness and its connection with risk and protective factors for health. Frontiers in Psychology, 6:1-10, 2015.","title":"Maite Garaigordobil. Predictor variables of happiness and its connection with risk and protective factors for health","authors":"Garaigordobil","year":"2015","venue":"Frontiers in Psychology","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Guo et al., 2017] Huifeng Guo, Ruiming Tang, and Yunming Ye et al. Deepfm: A factorization-machine based neural network for CTR prediction. In IJCAI, pages 1725-1731, 2017.","title":"Deepfm: A factorization-machine based neural network for CTR prediction","authors":"Guo","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/239"},{"position":14,"raw":"[He and Chua, 2017] Xiangnan He and Tat-Seng Chua. Neural fac- torization machines for sparse predictive analytics. In SIGIR, pages 355-364, 2017.","title":"Xiangnan He and Tat-Seng Chua. Neural factorization machines for sparse predictive analytics","authors":"Chua He","year":"2017","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Huang, 2017] Liqing Huang. Well-being of youth groups: An analysis based on cgss. China Youth Study, (12):53-59, 2017.","title":"Well-being of youth groups: An analysis based on cgss","authors":"Liqing Huang","year":"2017","venue":"China Youth Study","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Islam and Goldwasser, 2020] Tunazzina Islam and Dan Gold- wasser. Does yoga make you happy? analyzing twitter user hap- piness using textual and temporal information. In IEEE BigData, pages 4241-4249, 2020.","title":"Tunazzina Islam and Dan Goldwasser. Does yoga make you happy? analyzing twitter user happiness using textual and temporal information","authors":"Goldwasser Islam","year":"2020","venue":"IEEE BigData","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Kotakorpi and Laamanen, 2010] Kaisa Kotakorpi and Jani-Petri Laamanen. Welfare state and life satisfaction: Evidence from public health care. Economica, 77(307):565-583, 2010.","title":"Welfare state and life satisfaction: Evidence from public health care","authors":"Laamanen Kotakorpi, Kaisa Kotakorpi, Jani-Petri Laamanen","year":"2010","venue":"Economica","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Li and Wang, 2015] Jing Li and Yuejin Wang. An analysis of the relationship between health and subjective well-being of farmers -based on a survey of 1000 farmers in 5 provinces. Chinese Rural Economy, (10):80-88, 2015.","title":"An analysis of the relationship between health and subjective well-being of farmers -based on a survey of 1000 farmers in 5 provinces","authors":"Wang ; ] Jing Li, Yuejin Li, Wang","year":"2015","venue":"Chinese Rural Economy","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Lin et al., 2014] Huijie Lin, Jia Jia, and Quan Guo et al. User- level psychological stress detection from social media using deep neural network. In ACM Multimedia, pages 507-516, 2014.","title":"Userlevel psychological stress detection from social media using deep neural network","authors":"Lin","year":"2014","venue":"ACM Multimedia","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[O'Donnell and Oswald, 2015] Gus O'Donnell and Andrew J Os- wald. National well-being policy and a weighted approach to human feelings. Ecol. Econ., 120:59-70, 2015.","title":"Gus O'Donnell and Andrew J Oswald. National well-being policy and a weighted approach to human feelings","authors":"O' Donnell, Oswald","year":"2015","venue":"Ecol. Econ","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Oshio et al., 2011] Takashi Oshio, Kayo Nozaki, and Miki Kobayashi. Relative income and happiness in asia: Evidence from nationwide surveys in china, japan, and korea. Soc. Indic. Res., 104:351-367, 2011.","title":"Relative income and happiness in asia: Evidence from nationwide surveys in china, japan, and korea","authors":"Takashi Oshio, Kayo Nozaki, Miki Kobayashi","year":"2011","venue":"Soc. Indic. Res","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Peng et al., 2018] Xuefeng Peng, Li-Kai Chi, and Jiebo Luo. The effect of pets on happiness: A large-scale multi-factor analy- sis using social multimedia. ACM Trans. Intell. Syst. Technol., 9(5):61-75, 2018.","title":"The effect of pets on happiness: A large-scale multi-factor analysis using social multimedia","authors":"Xuefeng Peng, Li-Kai Chi, Jiebo Luo","year":"2018","venue":"ACM Trans. Intell. Syst. Technol","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Pérez-Benito et al., 2019] Francisco Javier Pérez-Benito, Patricia Villacampa-Fernández, J. Alberto Conejero, Juan M. García- Gómez, and Esperanza Navarro-Pardo. A happiness degree pre- dictor using the conceptual data structure for deep learning archi- tectures. Comput. Methods Programs Biomed., 168:59-68, 2019.","title":"A happiness degree predictor using the conceptual data structure for deep learning architectures","authors":"Pérez-Benito","year":"2019","venue":"Comput. Methods Programs Biomed","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Poria et al., 2015] Soujanya Poria, Erik Cambria, and Alexander F. Gelbukh. Deep convolutional neural network textual features and multiple kernel learning for utterance-level multimodal sentiment analysis. In EMNLP, pages 2539-2544, 2015.","title":"Deep convolutional neural network textual features and multiple kernel learning for utterance-level multimodal sentiment analysis","authors":"Poria","year":"2015","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Saputri and Lee, 2015] Theresia Ratih Dewi Saputri and Seok- Won Lee. A study of cross-national differences in happiness fac- tors using machine learning approach. Int. J. Softw. Eng. Knowl. Eng., 25(9-10):1699-1702, 2015.","title":"A study of cross-national differences in happiness factors using machine learning approach","authors":"Theresia Ratih, Dewi Saputri, Seok-Won Lee","year":"2015","venue":"Int. J. Softw. Eng. Knowl. Eng","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Shin, 2018] Inyong Shin. Could pension system make us happier? Cogent economics & finance, 6(1):1452342-1452367, 2018.","title":"Inyong Shin. Could pension system make us happier","authors":"Shin","year":"2018","venue":"Cogent economics & finance","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Strumbelj and Kononenko, 2014] Erik Strumbelj and Igor Kononenko. Explaining prediction models and individual predictions with feature contributions. Knowl. Inf. Syst., 41(3):647-665, 2014.","title":"Erik Strumbelj and Igor Kononenko. Explaining prediction models and individual predictions with feature contributions","authors":"Kononenko Strumbelj","year":"2014","venue":"Knowl. Inf. Syst","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Sweeney et al., 2021] Colm Sweeney, Edel Ennis, Raymond R. Bond, Maurice D. Mulvenna, and Siobhan O'Neill. Understand- ing a happiness dataset: How the machine learning classifica- tion accuracy changes with different demographic groups. In IEEE Symposium on Computers and Communications, pages 1- 4, 2021.","title":"Understanding a happiness dataset: How the machine learning classification accuracy changes with different demographic groups","authors":"Colm Sweeney, Edel Ennis, Raymond R Bond, Maurice D Mulvenna, Siobhan O' Neill","year":"2021","venue":"IEEE Symposium on Computers and Communications","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Tang et al., 2012] Jialin Tang, Zuoshan Li, and Xiaoyan Zhang. Relationship between university students' positive psychological capital and subjective well-being. Chinese Journal of Health Psy- chology, 020(007):1105-1108, 2012.","title":"Relationship between university students' positive psychological capital and subjective well-being","authors":"Jialin Tang, Zuoshan Li, Xiaoyan Zhang","year":"2012","venue":"Chinese Journal of Health Psychology","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Tao et al., 2021] Xiaohui Tao, Oliver Chi, Patrick J. Delaney, Lin Li, and Jiajin Huang. Detecting depression using an ensem- ble classifier based on quality of life scales. Brain Informatics, 8(1):2, 2021.","title":"Detecting depression using an ensemble classifier based on quality of life scales","authors":"Xiaohui Tao, Oliver Chi, Patrick J Delaney, Lin Li, Jiajin Huang","year":"2021","venue":"Brain Informatics","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Tella and MacCulloch, 2006] Rafael Di Tella and Robert MacCul- loch. Some uses of happiness data in economics. Journal of Economic Perspectives, 20(1):25-46, 2006.","title":"Rafael Di Tella and Robert MacCulloch. Some uses of happiness data in economics","authors":"Tella, Macculloch","year":"2006","venue":"Journal of Economic Perspectives","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Xin and Inkpen, 2019] Weizhao Xin and Diana Inkpen. Happi- ness ingredients detection using multi-task deep learning. In Af- fCon@AAAI, pages 164-170, 2019.","title":"Happiness ingredients detection using multi-task deep learning","authors":"Inkpen Xin, Weizhao Xin, Diana Inkpen","year":"2019","venue":"Af-fCon@AAAI","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Xu and Chen, 2017] Shuyi Xu and Ping Chen. Income, social sta- tus and happiness: From the perspective of equity perception. Journal of Management Science, 20(12):99-116, 2017.","title":"Income, social status and happiness: From the perspective of equity perception","authors":"Shuyi Xu, Ping Chen","year":"2017","venue":"Journal of Management Science","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}