�ݺ�ߣshows by User: ahandrew

�ݺ�ߣshows by User: ahandrew / http://www.slideshare.net/images/logo.gif �ݺ�ߣshows by User: ahandrew / Mon, 10 Mar 2014 11:23:13 GMT �ݺ�ߣShare feed for �ݺ�ߣshows by User: ahandrew Contextual Sensing and Sentiment Classification /slideshow/contextual-sensing-and-sentiment-classification/32132681 sentimentsymposiumfinal-140310112313-phpapp02
Traditionally, sentiment classification uses models trained on example phrases that are coded for desired sentiment. When constrained to a corpus of well-constrained utterances, such as product reviews on a website, this approach works well. We argue sentiment classification for less constrained corpora can be improved by considering context. Context can simply be the current location of a person, or as complex as knowing the person is at work after a longer than usual day. Context and sentiment classification can be combined in two ways. First, contextual information can improve sentiment classification of text. Information such as where a person was when they created the text could help interpret the content or sentiment behind the text, particularly with content that might be sarcastic or ironic. Second, we can apply sentiment classification techniques to contextual data streams to identify the sentiment of a person at a point in time.For example, knowing that a person had a fairly busy day after not sleeping well could identify that person as tired or grumpy. This can be derived from information such as a wearable sleep sensor and calendar information, activity sensors, or location information, all of which can be derived from sensors on a mobile phone.]]>
Traditionally, sentiment classification uses models trained on example phrases that are coded for desired sentiment. When constrained to a corpus of well-constrained utterances, such as product reviews on a website, this approach works well. We argue sentiment classification for less constrained corpora can be improved by considering context. Context can simply be the current location of a person, or as complex as knowing the person is at work after a longer than usual day. Context and sentiment classification can be combined in two ways. First, contextual information can improve sentiment classification of text. Information such as where a person was when they created the text could help interpret the content or sentiment behind the text, particularly with content that might be sarcastic or ironic. Second, we can apply sentiment classification techniques to contextual data streams to identify the sentiment of a person at a point in time.For example, knowing that a person had a fairly busy day after not sleeping well could identify that person as tired or grumpy. This can be derived from information such as a wearable sleep sensor and calendar information, activity sensors, or location information, all of which can be derived from sensors on a mobile phone.]]> Mon, 10 Mar 2014 11:23:13 GMT /slideshow/contextual-sensing-and-sentiment-classification/32132681 ahandrew@slideshare.net(ahandrew) Contextual Sensing and Sentiment Classification ahandrew Traditionally, sentiment classification uses models trained on example phrases that are coded for desired sentiment. When constrained to a corpus of well-constrained utterances, such as product reviews on a website, this approach works well. We argue sentiment classification for less constrained corpora can be improved by considering context. Context can simply be the current location of a person, or as complex as knowing the person is at work after a longer than usual day. Context and sentiment classification can be combined in two ways. First, contextual information can improve sentiment classification of text. Information such as where a person was when they created the text could help interpret the content or sentiment behind the text, particularly with content that might be sarcastic or ironic. Second, we can apply sentiment classification techniques to contextual data streams to identify the sentiment of a person at a point in time.For example, knowing that a person had a fairly busy day after not sleeping well could identify that person as tired or grumpy. This can be derived from information such as a wearable sleep sensor and calendar information, activity sensors, or location information, all of which can be derived from sensors on a mobile phone. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/sentimentsymposiumfinal-140310112313-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" /> Traditionally, sentiment classification uses models trained on example phrases that are coded for desired sentiment. When constrained to a corpus of well-constrained utterances, such as product reviews on a website, this approach works well. We argue sentiment classification for less constrained corpora can be improved by considering context. Context can simply be the current location of a person, or as complex as knowing the person is at work after a longer than usual day. Context and sentiment classification can be combined in two ways. First, contextual information can improve sentiment classification of text. Information such as where a person was when they created the text could help interpret the content or sentiment behind the text, particularly with content that might be sarcastic or ironic. Second, we can apply sentiment classification techniques to contextual data streams to identify the sentiment of a person at a point in time.For example, knowing that a person had a fairly busy day after not sleeping well could identify that person as tired or grumpy. This can be derived from information such as a wearable sleep sensor and calendar information, activity sensors, or location information, all of which can be derived from sensors on a mobile phone.

Contextual Sensing and Sentiment Classification from Adrienne Andrew

]]> 548 2 https://cdn.slidesharecdn.com/ss_thumbnails/sentimentsymposiumfinal-140310112313-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 The Value of Location Lifelogging for Health & Wellness /ahandrew/aro-lifelogging-presv1-26705399 arolifeloggingpresv1-130930132201-phpapp01
I discuss how combining location and body/activity sensors can provide value to people struggling to change their health and wellness behaviors. ]]>
I discuss how combining location and body/activity sensors can provide value to people struggling to change their health and wellness behaviors. ]]> Mon, 30 Sep 2013 13:22:01 GMT /ahandrew/aro-lifelogging-presv1-26705399 ahandrew@slideshare.net(ahandrew) The Value of Location Lifelogging for Health & Wellness ahandrew I discuss how combining location and body/activity sensors can provide value to people struggling to change their health and wellness behaviors. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/arolifeloggingpresv1-130930132201-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /> I discuss how combining location and body/activity sensors can provide value to people struggling to change their health and wellness behaviors.

The Value of Location Lifelogging for Health & Wellness from Adrienne Andrew

]]> 748 3 https://cdn.slidesharecdn.com/ss_thumbnails/arolifeloggingpresv1-130930132201-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Simplifying Mobile Phone Food Diaries /slideshow/andrew-ph-presslideshare/26705342 andrewphpresslideshare-130930132020-phpapp01
I describe the design of a novel mobile phone food diary and an initial user evaluation. ]]>
I describe the design of a novel mobile phone food diary and an initial user evaluation. ]]> Mon, 30 Sep 2013 13:20:20 GMT /slideshow/andrew-ph-presslideshare/26705342 ahandrew@slideshare.net(ahandrew) Simplifying Mobile Phone Food Diaries ahandrew I describe the design of a novel mobile phone food diary and an initial user evaluation. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/andrewphpresslideshare-130930132020-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /> I describe the design of a novel mobile phone food diary and an initial user evaluation.

Simplifying Mobile Phone Food Diaries from Adrienne Andrew

]]> 581 6 https://cdn.slidesharecdn.com/ss_thumbnails/andrewphpresslideshare-130930132020-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation White http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Simplifying Mobile Phone Food Diaries with Food Indexes /slideshow/simplifying-mobile-phone-food-diaries-with-food-indexes/26705135 andrewmedxsunslideshare-130930131542-phpapp02
Presented at MedX 2013. ]]>
Presented at MedX 2013. ]]> Mon, 30 Sep 2013 13:15:42 GMT /slideshow/simplifying-mobile-phone-food-diaries-with-food-indexes/26705135 ahandrew@slideshare.net(ahandrew) Simplifying Mobile Phone Food Diaries with Food Indexes ahandrew Presented at MedX 2013. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/andrewmedxsunslideshare-130930131542-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" /> Presented at MedX 2013.

Simplifying Mobile Phone Food Diaries with Food Indexes from Adrienne Andrew

]]> 656 6 https://cdn.slidesharecdn.com/ss_thumbnails/andrewmedxsunslideshare-130930131542-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Approaches to Food Journaling on Mobile Devices /slideshow/approaches-to-food-journaling-on-mobile-devices/13870151 andrewfinalexam-120804080537-phpapp02
]]>
]]> Sat, 04 Aug 2012 08:05:35 GMT /slideshow/approaches-to-food-journaling-on-mobile-devices/13870151 ahandrew@slideshare.net(ahandrew) Approaches to Food Journaling on Mobile Devices ahandrew <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/andrewfinalexam-120804080537-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" />

Approaches to Food Journaling on Mobile Devices from Adrienne Andrew

]]> 806 4 https://cdn.slidesharecdn.com/ss_thumbnails/andrewfinalexam-120804080537-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 https://cdn.slidesharecdn.com/profile-photo-ahandrew-48x48.jpg?cb=1628814222 https://cdn.slidesharecdn.com/ss_thumbnails/sentimentsymposiumfinal-140310112313-phpapp02-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/contextual-sensing-and-sentiment-classification/32132681 Contextual Sensing and... https://cdn.slidesharecdn.com/ss_thumbnails/arolifeloggingpresv1-130930132201-phpapp01-thumbnail.jpg?width=320&height=320&fit=bounds ahandrew/aro-lifelogging-presv1-26705399 The Value of Location ... https://cdn.slidesharecdn.com/ss_thumbnails/andrewphpresslideshare-130930132020-phpapp01-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/andrew-ph-presslideshare/26705342 Simplifying Mobile Pho...