Thanks Harsha. Yes, I know about the Fisher Callhome Corpus. There is data related in there that can be used for sentiment analysis :) It can be adapted and is being used for that.
Anyways, yes looking forward to the task. Please send in your proposal Madhawa. ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Chris Mattmann, Ph.D. Chief Architect Instrument Software and Science Data Systems Section (398) NASA Jet Propulsion Laboratory Pasadena, CA 91109 USA Office: 168-519, Mailstop: 168-527 Email: chris.a.mattm...@nasa.gov WWW: http://sunset.usc.edu/~mattmann/ ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Director, Information Retrieval and Data Science Group (IRDS) Adjunct Associate Professor, Computer Science Department University of Southern California, Los Angeles, CA 90089 USA WWW: http://irds.usc.edu/ ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ -----Original Message----- From: Harshavardhan Manjunatha <hmanj...@usc.edu> Date: Friday, March 25, 2016 at 2:45 PM To: jpluser <chris.a.mattm...@jpl.nasa.gov> Cc: "d...@opennlp.apache.org" <d...@opennlp.apache.org>, Information and Data Science Group USC List <ird...@mymaillists.usc.edu>, "kamal...@usc.edu" <kamal...@usc.edu>, "dev@tika.apache.org" <dev@tika.apache.org> Subject: Re: GSOC2016 Sentiment Analysis >Dear Prof. Mattmann, > > >Thanks. But the Fisher Callhome Corpus is a training Corpus for Machine >Translation b/w Spanish & Englosh. > > >I dont think it can be adapted to Sentiment Analysis. > > >Developing a generic training model/corpus for Sentiment Analysis that >encapsulates social media, movie reviews, etc, etc will be a Challenging >& Exciting Task !! > > >Regards, >Harsha > > >On Fri, Mar 25, 2016 at 2:42 PM, Mattmann, Chris A (3980) ><chris.a.mattm...@jpl.nasa.gov> wrote: > >Sounds great Harsha. This is for Google Summer of Code, so collaborating >would be great, and in this case, we would be working with Madhawa, should >he choose to accept. > >++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ >Chris Mattmann, Ph.D. >Chief Architect >Instrument Software and Science Data Systems Section (398) >NASA Jet Propulsion Laboratory Pasadena, CA 91109 USA >Office: 168-519, Mailstop: 168-527 >Email: chris.a.mattm...@nasa.gov >WWW: >http://sunset.usc.edu/~mattmann/ <http://sunset.usc.edu/~mattmann/> >++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ >Director, Information Retrieval and Data Science Group (IRDS) >Adjunct Associate Professor, Computer Science Department >University of Southern California, Los Angeles, CA 90089 USA >WWW: http://irds.usc.edu/ >++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ > > > > > >-----Original Message----- >From: Harshavardhan Manjunatha <hmanj...@usc.edu> >Date: Friday, March 25, 2016 at 2:38 PM >To: jpluser <chris.a.mattm...@jpl.nasa.gov> >Cc: "d...@opennlp.apache.org" <d...@opennlp.apache.org>, Information and >Data Science Group USC List <ird...@mymaillists.usc.edu>, >"kamal...@usc.edu" <kamal...@usc.edu>, "dev@tika.apache.org" ><dev@tika.apache.org> >Subject: Re: GSOC2016 Sentiment Analysis > >>Dear Prof. Mattmann, >> >> >>I would love to collaborate on this & am interested in developing >>Sentiment Analysis Tika Parsers leveraging Apache OpenNLP. >> >> >>I have completed an Applied NLP course @ USC. >> >> >>I have done a Literature Review of Papers & Open Source Tools on the same >>recently. >> >> >>Regards, >>Harsha >> >> >>On Fri, Mar 25, 2016 at 2:07 PM, Mattmann, Chris A (3980) >><chris.a.mattm...@jpl.nasa.gov> wrote: >> >>Hi Madhawa, >> >> >> >>So, how about a project that develops and contributes an Apache >> >>Tika and OpenNLP based SentimentAnalysisParser? >> >> >> >>I have some students currently doing work using the Fisher Callhome >> >>Corpus and you can build off that. I am CC’ing my USC IRDS team >> >>and my student Indhu who is working on this. >> >> >> >>Can you start working on your proposal by: >> >> >> >>1. Creating a JIRA issue here: >> >>https://urldefense.proofpoint.com/v2/url?u=http-3A__issues.apache.org_jir >>a >>_browse_TIKA&d=CwIGaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=8l5 >>6 >>W6EU8xpHKOeTqpG03w&m=FEfICxmcDheHndXqky_rLNiYMcQE9yeOn7RoOwpR8t0&s=BPBK1m >>s >>1hzt9Tb5RdkU5B7FqRxuyMu3BoROpgd8Tvdw&e= >> >> tag it with ‘gsoc2016’, ‘memex’, and ‘irds’ please >> >> >> >>2. Develop a proposal on the Tika wiki here: >> >>https://urldefense.proofpoint.com/v2/url?u=http-3A__wiki.apache.org_tika_ >>G >>SoC2016&d=CwIGaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=8l56W6EU >>8 >>xpHKOeTqpG03w&m=FEfICxmcDheHndXqky_rLNiYMcQE9yeOn7RoOwpR8t0&s=GGQdxogPSoN >>h >>rlr5mALyeK4Jkn7og7u5K0Mr6qGuQ1s&e= >> (you will need permission, first >> >>sign up for your account on the wiki then tell me your username so I >> >>can add permissions for you) >> >> >> >>3. Apply through the Google Summer of Code 2016 program. >> >> >> >>4. Get in touch with me, and Indhu, and keep dev@tika.a.o and >> >>dev@openlp.a.o and ird...@usc.edu in the loop so we can discuss together >> >>as a community. >> >> >> >>Cool? >> >> >> >>Cheers, >> >>Chris >> >> >> >>++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ >> >>Chris Mattmann, Ph.D. >> >>Chief Architect >> >>Instrument Software and Science Data Systems Section (398) >> >>NASA Jet Propulsion Laboratory Pasadena, CA 91109 USA >> >>Office: 168-519, Mailstop: 168-527 >> >>Email: chris.a.mattm...@nasa.gov >> >>WWW: > > >>http://sunset.usc.edu/~mattmann/ <http://sunset.usc.edu/~mattmann/> >> >>++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ >> >>Director, Information Retrieval and Data Science Group (IRDS) >> >>Adjunct Associate Professor, Computer Science Department >> >>University of Southern California, Los Angeles, CA 90089 USA >> >>WWW: http://irds.usc.edu/ >> >>++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ >> >> >> >> >> >> >> >> >> >> >> >>-----Original Message----- >> >>From: Madhawa Kasun Gunasekara <madhaw...@gmail.com> >> >>Reply-To: "d...@opennlp.apache.org" <d...@opennlp.apache.org> >> >>Date: Wednesday, March 16, 2016 at 10:51 PM >> >>To: "d...@opennlp.apache.org" <d...@opennlp.apache.org> >> >>Subject: GSOC2016 Sentiment Analysis >> >> >> >>>Hi >> >>> >> >>>I am interesting on contribute to OPENNLP-840: "Sentiment Analysis" for >> >>>GSOC2016 this time. Since i have been engaging with some similar >>>projects >> >>>i >> >>>think it will be a great experience for me. >> >>> >> >>>I am a final year student in IESL College of Engineering, Sri lanka. I >> >>>have >> >>>learned machine learning and natural language processing stuff when I'm >> >>>doing my first degree (Computer Science) in University of Sri >> >>>Jayewardhenapura. >> >>> >> >>>In my internship period, I have actively contributed to a Twitter based >> >>>NLP >> >>>project. and We have published an article on IEEE Conference, "Real-time >> >>>Natural Language Processing for Crowdsourced Road Traffic Alerts" [2] . >> >>> >> >>>Please let me know what you think and what you suggest. >> >>> >> >>>Please kindly give me further information on how I could proceed. I >> >>>couldn't able to find the mentioned paper "Multi-Class Sentiment >>>Analysis >> >>>in Twitter: a Pattern-Based Approach" >> >>>[1] >>https://urldefense.proofpoint.com/v2/url?u=https-3A__issues.apache.org_ji >>r >>a_browse_OPENNLP-2D840&d=CwIGaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfn >>c >>_gI&r=8l56W6EU8xpHKOeTqpG03w&m=FEfICxmcDheHndXqky_rLNiYMcQE9yeOn7RoOwpR8t >>0 >>&s=p9CPiDKtrgF3BYZ8nLSWUXFncDjBBYV2ejUW4wPXtCY&e= > > >><https://urldefense.proofpoint.com/v2/url?u=https-3A__issues.apache.org_j >>i >>ra_browse_OPENNLP-2D840&d=CwIGaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSf >>n >>c_gI&r=8l56W6EU8xpHKOeTqpG03w&m=FEfICxmcDheHndXqky_rLNiYMcQE9yeOn7RoOwpR8 >>t >>0&s=p9CPiDKtrgF3BYZ8nLSWUXFncDjBBYV2ejUW4wPXtCY&e=> >> >>>[2] >>https://urldefense.proofpoint.com/v2/url?u=http-3A__ieeexplore.ieee.org_x >>p >>l_articleDetails.jsp-3Farnumber-3D7377667&d=CwIGaQ&c=clK7kQUTWtAVEOVIgvi0 >>N >>U5BOUHhpN0H8p7CSfnc_gI&r=8l56W6EU8xpHKOeTqpG03w&m=FEfICxmcDheHndXqky_rLNi >>Y >>McQE9yeOn7RoOwpR8t0&s=V6EFcS7WaMwDxGZ5Ttm5-f-UTMLBlmIIBgkJYHB7P1w&e= >><https://urldefense.proofpoint.com/v2/url?u=http-3A__ieeexplore.ieee.org_ >>x >>pl_articleDetails.jsp-3Farnumber-3D7377667&d=CwIGaQ&c=clK7kQUTWtAVEOVIgvi >>0 >>NU5BOUHhpN0H8p7CSfnc_gI&r=8l56W6EU8xpHKOeTqpG03w&m=FEfICxmcDheHndXqky_rLN >>i >>YMcQE9yeOn7RoOwpR8t0&s=V6EFcS7WaMwDxGZ5Ttm5-f-UTMLBlmIIBgkJYHB7P1w&e=> >> >>> >> >>>Thanks >> >>>Madhawa Gunasekara >> >> >> >> >> >> >> >> > > > > > >
