Developers

Arabic and Japanese support is now available for IBM Watson Personality Insights

Share this post:

Personality Insights was announced as Generally Available in February 2015. In July 2015, support for Spanish was announced. Individual developers, IBM Watson ecosystem partners, and large enterprises are building new solutions and integrating this service into existing applications across a large number of industries. Their use cases include understanding their customers at a deeper level for more effective engagement and offering  more personalized products, services and offers.

More details on Arabic and Japanese language support are as follows:

  •  Arabic models are now available
    This feature allows applying Personality Insights to derive personality, values, and needs from Modern Standard Arabic (MSA) input text written in Arabic script. In addition, as many social media posts mix both Arabic and English, this model supports both languages. For example, if a text sample has a given sentence that contains both English and Arabic words, a single complete profile that uses content from both languages, will be created.

We analyzed the tweets shared by Mohamed Abou Trika (@trikaofficial) using the personality model and get the following personality portrait. He is among the highest, when compared to other Arabic tweeters, in openness, conscientiousness, challenging himself and helping others. Based on his personality, he is likely to show behaviors such as buying healthy and re-sharing content on social media.

picq

  • Japanese models are now available
    This feature allows applying Personality Insights to derive personality, values, and needs from Japanese input text. However, in this case any non-Japanese text in the input is ignored.

We analyzed the tweets by ダルビッシュ有  (Yu Darvish), currently a pitcher for the Texas Rangers Baseball Team. His portrait showed him to be self-assured, calm and content with himself. He cares about helping others, and having novel experiences. Based on his personality, he is likely to show behaviors such as buying eco-friendly products, but unlikely to click on ads.

pic2

Try out these new languages on our demo.

The technical team responsible for personality insights includes: Neil Boyette, Pierre Arnoux, Agustin Casamayor, Shubhanjan Shekhar, Vibha Sinha, Jalal Mahmud and Rama Akkiraju. Kenneth Kuo is the offering manager.

The Arabic support was created with the assistance from Salim Roukos, Juergen Bross, Abe Ittycheriah, Andy Sakrajda and Rong Zhang from the Watson Natural Language Systems group.

The Japanese support was created with assistance from Akihiro Nakayama, Kohichi Kamijoh, Tetsuya Nasukawa, Sachiko Yoshihama, Hideshi Yoshinaga, Kohichi Takeda, and Seiji Hamada from the IBM Tokyo Research Lab.

Try out these new languages on our demo

 

More Developers stories

Behind the Code: Meet Young-Suk Lee

August 4, 2020 | Trends and Profiles

Young-Suk Lee first learned about machine translation while studying English linguistics and literature. Now as a machine translation developer, she works on the multilingual systems that power Watson Language Translator. We talked to her about her first exposure to machine learning tech, the themes that run through her multiple projects, how she draws inspiration from ...read more


CodeObjects + IBM: The best customer experience in the worst of times

August 3, 2020 | AI for the Enterprise, Conversational Services

When a hurricane hits, the last thing homeowners (or their insurers) need, or want, is to be on hold for hours to submit a claim. But with call volumes dramatically exceeding norms, that’s always been inevitable. Until now. In 2018, within less than a week, Hurricane Michael suddenly became a major Category 5 storm and ...read more


IBM Innovation Preview: Automation of AI

July 22, 2020 | AI for the Enterprise

IBM’s second Innovation Preview event features AI experts and IBM executives as they share exciting new developments made by IBM Research in the field of Automation of AI. In the event, now available online, these leaders present three ways to leverage automation for AI: Accurately digitize and streamline workflows to become more efficient and adaptable ...read more