Open data - Download the Knowledge base
You are free to download the data of this Knowledge base.
To do this you must be an authenticated user: log in or sign in now.
All the data are licensed as Creative Common CC-BY 4.0.
Semantria
Semantria is a tool that offers a unique service approach by gathering texts, tweets, and other comments from clients and analysing them meticulously to derive actionable and highly valuable insights. Semantria offers text analysis via API and Excel plugin, incorporates a big knowledge base and uses deep learning
Type of content:
Assets
Type of asset:
Tool
Big data potential
Yes
Policy domains:
Innovation, Science & Technology
Phase in the policy cycle:
Policy Design and Analysis
TRL
8
Open license availability
Yes
Tags:
BI
Data analytics
Real time information
Serves:
| SWOT Analysis for Semantria |
||
|---|---|---|
| Helpful | Harmful | |
Internal |
Strengths• Monitor consumer sentiment in real-time and over time • Catch trending topics before they go viral • Identify problems before they blow up • Capitalize on hype cycles to grow brand awareness • Multi-User Seat Packages • Categorization • It's easy to perform text analysis in Excel as Semantria for Excel provides fast and accurate categorization of your input content. • Easy Customization • Multilingual for All Industries • Visualization: Use the Excel visualization tools you're already familiar with to create rich charts and graphs: all the results are displayed in simple visual terms, while retaining the deep insights Lexalytics is known for. • Is offered via API and Excel plugin, and in that it incorporates a bigger knowledge base and uses deep learning. |
Weaknesses• Low ease of use • High implementation /customization cost: extra pricing option for more languages • Limited transactions for basic license |
External |
Opportunities• Sentiment analysis (SA) techniques are commonly based on textual sources. In fact, many other multimedia sources should also be processed, some of which are important sources for examples exhibiting expressions of mocking, sabotaging and sarcasm, which are sensitive content for companies’ reputations and for competitiveness planning. Therefore, multi-modal SA techniques are going to be in high demand • Brand monitoring: Monitor the sentiment around a brand and its products. • Campaign monitoring: Create and follow the development of a marketing campaign as it unfolds within internal and external content channels. • Competitive intelligence: Follow competitors and assess the perception of customers around their activities. • Identifying influencers: Find out who is talking about your brand, campaign across several channels. |
Threats• The velocity issue relates closely with the volume and variety, because the data is generated continuously and thus increases the challenge in its analysis • Data quality: social media messages are by nature shorter and generally not constructed with proper grammatical rules and hence may decrease the text classification accuracy • Need for continuous evolution: depending on an ad-hoc or one-off developed model without continuous adaptation and evolving ability might result in limiting the power of the social media analysis • Difficulty in recognizing things like sarcasm and irony, negations, jokes, and exaggerations. • Trustworthiness of the data: Determining trustworthiness of the data demands more norms and logical reasoning which should be considered using many factors and not limited to only the current message being processed but also other messages being posted by the same message sender, for his profile to be considered. • Quality of data: SA techniques should be updated to be able to reason and determine the levels of uncertainty, validity, messiness and trustworthiness of the data. The quality and accuracy of the developed model must be prioritized. SA algorithms for filtering and pre-processing also have to be updated, to process and consider data which are curated with low control and are possibly meaningless. |
