@article{stinson_w2vpca_nodate,
	title = {{W2VPCA}: {A} {Method} for {Measuring} {Latent} {Strategies} {Using} {Existing} {Text} {Data}},
	url = {https://anl.box.com/s/osabg86qex0y0j1mx3c4hjd7gwzikqjm},
	abstract = {This study introduces an innovative, new, machine learning method to generate strategy measurement
data from existing text. Strategy is a major driver of business firm decisions, including decisions
regarding freight transportation. Behavioral freight models could benefit from including strategy
variables. However, strategy is difficult to observe and quantify. Attitudinal surveys of company
executives can be used to collect measurements of latent strategy for subsequent use in quantitative
models. However, surveys are costly and burdensome. Text mining methods to collect measurements
overcome these issues somewhat, but typically require manual intervention and ignore the context of
words, which can be problematic. We develop a Natural Language Processing-based method called
W2VPCA, which produces measurement data that serve as quantitative indicators of latent strategy in
behavioral models. W2VPCA is unsupervised, data-driven, and uses information on word context. We
apply W2VPCA to generate measurements of latent strategies using annual company reports. Using our empirical measurements, we associate two latent strategies, one focusing on distribution and the other on products, with truck fleet and distribution center outsourcing decisions.},
	journal = {In submission to journal},
	author = {Stinson, Monique and Mohammadian, Abolfazl},
}

{"_id":"MNKpmS6Mig2TjBW5d","bibbaseid":"stinson-mohammadian-w2vpcaamethodformeasuringlatentstrategiesusingexistingtextdata","author_short":["Stinson, M.","Mohammadian, A."],"bibdata":{"bibtype":"article","type":"article","title":"W2VPCA: A Method for Measuring Latent Strategies Using Existing Text Data","url":"https://anl.box.com/s/osabg86qex0y0j1mx3c4hjd7gwzikqjm","abstract":"This study introduces an innovative, new, machine learning method to generate strategy measurement data from existing text. Strategy is a major driver of business firm decisions, including decisions regarding freight transportation. Behavioral freight models could benefit from including strategy variables. However, strategy is difficult to observe and quantify. Attitudinal surveys of company executives can be used to collect measurements of latent strategy for subsequent use in quantitative models. However, surveys are costly and burdensome. Text mining methods to collect measurements overcome these issues somewhat, but typically require manual intervention and ignore the context of words, which can be problematic. We develop a Natural Language Processing-based method called W2VPCA, which produces measurement data that serve as quantitative indicators of latent strategy in behavioral models. W2VPCA is unsupervised, data-driven, and uses information on word context. We apply W2VPCA to generate measurements of latent strategies using annual company reports. Using our empirical measurements, we associate two latent strategies, one focusing on distribution and the other on products, with truck fleet and distribution center outsourcing decisions.","journal":"In submission to journal","author":[{"propositions":[],"lastnames":["Stinson"],"firstnames":["Monique"],"suffixes":[]},{"propositions":[],"lastnames":["Mohammadian"],"firstnames":["Abolfazl"],"suffixes":[]}],"bibtex":"@article{stinson_w2vpca_nodate,\n\ttitle = {{W2VPCA}: {A} {Method} for {Measuring} {Latent} {Strategies} {Using} {Existing} {Text} {Data}},\n\turl = {https://anl.box.com/s/osabg86qex0y0j1mx3c4hjd7gwzikqjm},\n\tabstract = {This study introduces an innovative, new, machine learning method to generate strategy measurement\ndata from existing text. Strategy is a major driver of business firm decisions, including decisions\nregarding freight transportation. Behavioral freight models could benefit from including strategy\nvariables. However, strategy is difficult to observe and quantify. Attitudinal surveys of company\nexecutives can be used to collect measurements of latent strategy for subsequent use in quantitative\nmodels. However, surveys are costly and burdensome. Text mining methods to collect measurements\novercome these issues somewhat, but typically require manual intervention and ignore the context of\nwords, which can be problematic. We develop a Natural Language Processing-based method called\nW2VPCA, which produces measurement data that serve as quantitative indicators of latent strategy in\nbehavioral models. W2VPCA is unsupervised, data-driven, and uses information on word context. We\napply W2VPCA to generate measurements of latent strategies using annual company reports. Using our empirical measurements, we associate two latent strategies, one focusing on distribution and the other on products, with truck fleet and distribution center outsourcing decisions.},\n\tjournal = {In submission to journal},\n\tauthor = {Stinson, Monique and Mohammadian, Abolfazl},\n}\n\n","author_short":["Stinson, M.","Mohammadian, A."],"key":"stinson_w2vpca_nodate","id":"stinson_w2vpca_nodate","bibbaseid":"stinson-mohammadian-w2vpcaamethodformeasuringlatentstrategiesusingexistingtextdata","role":"author","urls":{"Paper":"https://anl.box.com/s/osabg86qex0y0j1mx3c4hjd7gwzikqjm"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://api.zotero.org/groups/2254223/items?key=Bbol5AZSx3A5fDcmq91mfOKd&format=bibtex&limit=100","dataSources":["WZSd6SdWp6wSKRgj6","rY8uL8LFtJi4FqTy8","qc6TuRNtLYeLyawhB","cGgmoLgbNTEZGWgPE","YAe24F3YNSozTyd4w"],"keywords":[],"search_terms":["w2vpca","method","measuring","latent","strategies","using","existing","text","data","stinson","mohammadian"],"title":"W2VPCA: A Method for Measuring Latent Strategies Using Existing Text Data","year":null}