Marchetto et al 2020a - Revision history

Scipediacontent at 23:20, 1 February 2021

2021-02-01T23:20:56Z

Scipediacontent at 17:07, 21 January 2021

2021-01-21T17:07:38Z

Scipediacontent: Scipediacontent moved page Draft Content 509923214 to Marchetto et al 2020a

2021-01-21T14:24:31Z

Scipediacontent moved page Draft Content 509923214 to Marchetto et al 2020a

Scipediacontent: Created page with " == Abstract == [EN] Mobile applications have become widely popular for their ability to access real-time information. In electric vehicle (EV) mobility, these applications a..."

2021-01-21T14:24:29Z

Created page with " == Abstract == [EN] Mobile applications have become widely popular for their ability to access real-time information. In electric vehicle (EV) mobility, these applications a..."

New page

== Abstract ==

[EN] Mobile applications have become widely popular for their ability to access real-time information. In electric vehicle (EV) mobility, these applications are used by drivers to locate charging stations in public spaces, pay for charging transactions, and engage with other users. This activity generates a rich source of data about charging infrastructure and behavior. However, an increasing share of this data is stored as unstructured textâinhibiting our ability to interpret behavior in real-time. In this article, we implement recent transformer-based deep learning algorithms, BERT and XLnet, that have been tailored to automatically classify short user reviews about EV charging experiences. We achieve classification results with a mean accuracy of over 91% and a mean F1 score of over 0.81 allowing for more precise detection of topic categories, even in the presence of highly imbalanced data. Using these classification algorithms as a pre-processing step, we analyze a U.S. national dataset with econometric methods to discover the dominant topics of discourse in charging infrastructure. After adjusting for station characteristics and other factors, we find that the functionality of a charging station is the dominant topic among EV drivers and is more likely to be discussed at points-of-interest with negative user experiences. Marchetto, D.; Ha, S.; Dharur, S.; Asensio, O. (2020). Extracting User Behavior at Electric Vehicle Charging Stations with Transformer Deep Learning Models. Editorial Universitat PolitÃ¨cnica de ValÃ¨ncia. 153-162. https://doi.org/10.4995/CARMA2020.2020.11613 OCS 153 162

== Original document ==

The different versions of the original document can be found in:

* [http://hdl.handle.net/10251/148979 http://hdl.handle.net/10251/148979]

* [http://ocs.editorial.upv.es/index.php/CARMA/CARMA2020/paper/download/11613/5706 http://ocs.editorial.upv.es/index.php/CARMA/CARMA2020/paper/download/11613/5706]

* [http://ocs.editorial.upv.es/index.php/CARMA/CARMA2020/paper/viewFile/11613/5706 http://ocs.editorial.upv.es/index.php/CARMA/CARMA2020/paper/viewFile/11613/5706],
: [http://dx.doi.org/10.4995/carma2020.2020.11613 http://dx.doi.org/10.4995/carma2020.2020.11613]

* [http://ocs.editorial.upv.es/index.php/CARMA/CARMA2020/paper/viewFile/11613/5706 http://ocs.editorial.upv.es/index.php/CARMA/CARMA2020/paper/viewFile/11613/5706],
: [https://academic.microsoft.com/#/detail/3043126173 https://academic.microsoft.com/#/detail/3043126173]

@@ Line 2: / Line 2: @@
 == Abstract ==
-[EN] Mobile applications have become widely popular for their ability to access real-time information. In electric vehicle (EV) mobility, these applications are used by drivers to locate charging stations in public spaces, pay for charging transactions, and engage with other users. This activity generates a rich source of data about charging infrastructure and behavior. However, an increasing share of this data is stored as unstructured text inhibiting our ability to interpret behavior in real-time. In this article, we implement recent transformer-based deep learning algorithms, BERT and XLnet, that have been tailored to automatically classify short user reviews about EV charging experiences. We achieve classification results with a mean accuracy of over 91% and a mean F1 score of over 0.81 allowing for more precise detection of topic categories, even in the presence of highly imbalanced data. Using these classification algorithms as a pre-processing step, we analyze a U.S. national dataset with econometric methods to discover the dominant topics of discourse in charging infrastructure. After adjusting for station characteristics and other factors, we find that the functionality of a charging station is the dominant topic among EV drivers and is more likely to be discussed at points-of-interest with negative user experiences. Marchetto, D.; Ha, S.; Dharur, S.; Asensio, O. (2020). Extracting User Behavior at Electric Vehicle Charging Stations with Transformer Deep Learning Models. Editorial Universitat Politénica de Valencia. 153-162. https://doi.org/10.4995/CARMA2020.2020.11613 OCS 153 162
+[EN] Mobile applications have become widely popular for their ability to access real-time information. In electric vehicle (EV) mobility, these applications are used by drivers to locate charging stations in public spaces, pay for charging transactions, and engage with other users. This activity generates a rich source of data about charging infrastructure and behavior. However, an increasing share of this data is stored as unstructured text—inhibiting our ability to interpret behavior in real-time. In this article, we implement recent transformer-based deep learning algorithms, BERT and XLnet, that have been tailored to automatically classify short user reviews about EV charging experiences. We achieve classification results with a mean accuracy of over 91% and a mean F1 score of over 0.81 allowing for more precise detection of topic categories, even in the presence of highly imbalanced data. Using these classification algorithms as a pre-processing step, we analyze a U.S. national dataset with econometric methods to discover the dominant topics of discourse in charging infrastructure. After adjusting for station characteristics and other factors, we find that the functionality of a charging station is the dominant topic among EV drivers and is more likely to be discussed at points-of-interest with negative user experiences. Marchetto, D.; Ha, S.; Dharur, S.; Asensio, O. (2020). Extracting User Behavior at Electric Vehicle Charging Stations with Transformer Deep Learning Models. Editorial Universitat Politècnica de València. 153-162. https://doi.org/10.4995/CARMA2020.2020.11613 OCS 153 162
 == Original document ==

← Older revision	Revision as of 14:24, 21 January 2021
(No difference)